Triple

T18368594

Position	Surface form	Disambiguated ID	Type / Status
Subject	Kathlamet language	`E440117`	entity
Predicate	hasSource	`P409`	FINISHED
Object	Smithsonian Institution linguistic collections The Smithsonian Institution linguistic collections are archival holdings of Indigenous and other world languages, preserving field notes, recordings, and documentation gathered by linguists and anthropologists for research and cultural heritage.	`E1321821`	NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini

Instruction

Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).

Input

Phrase: Smithsonian Institution linguistic collections | Statement: [Kathlamet language, hasSource, Smithsonian Institution linguistic collections]

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: Smithsonian Institution linguistic collections
Context triple: [Kathlamet language, hasSource, Smithsonian Institution linguistic collections]

A. The Language Archive
The Language Archive is a poignant stage play by Julia Cho that explores love, communication, and the limits of language through the story of a linguist struggling to understand the people closest to him.
B. The Atlas of Languages
The Atlas of Languages is a comprehensive reference work that surveys the world’s linguistic diversity, mapping and describing languages, language families, and their global distribution.
C. Glottolog
Glottolog is a comprehensive bibliographic and classification database of the world’s languages and dialects, maintained by linguists at the Max Planck Institute.
D. Archi Language Corpus
Archi Language Corpus is a digital collection of texts and linguistic data documenting the Archi language for research and preservation purposes.
E. Alan Lomax Collection at the American Folklife Center
The Alan Lomax Collection at the American Folklife Center is a major archival repository of field recordings, photographs, films, and documentation of traditional music and oral culture gathered by folklorist Alan Lomax from around the world.
F. None of above. chosen
G. Unsure - the case is ambiguous/there is not enough information to decide.

NEDg Description generation gpt-5.1

Instruction

Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"

Input

Entity: Smithsonian Institution linguistic collections
Triple: [Kathlamet language, hasSource, Smithsonian Institution linguistic collections]

Generated description

The Smithsonian Institution linguistic collections are archival holdings of Indigenous and other world languages, preserving field notes, recordings, and documentation gathered by linguists and anthropologists for research and cultural heritage.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: Smithsonian Institution linguistic collections
Target entity description: The Smithsonian Institution linguistic collections are archival holdings of Indigenous and other world languages, preserving field notes, recordings, and documentation gathered by linguists and anthropologists for research and cultural heritage.

A. The Language Archive
The Language Archive is a poignant stage play by Julia Cho that explores love, communication, and the limits of language through the story of a linguist struggling to understand the people closest to him.
B. The Atlas of Languages
The Atlas of Languages is a comprehensive reference work that surveys the world’s linguistic diversity, mapping and describing languages, language families, and their global distribution.
C. Glottolog
Glottolog is a comprehensive bibliographic and classification database of the world’s languages and dialects, maintained by linguists at the Max Planck Institute.
D. Archi Language Corpus
Archi Language Corpus is a digital collection of texts and linguistic data documenting the Archi language for research and preservation purposes.
E. Alan Lomax Collection at the American Folklife Center
The Alan Lomax Collection at the American Folklife Center is a major archival repository of field recordings, photographs, films, and documentation of traditional music and oral culture gathered by folklorist Alan Lomax from around the world.
F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step	Stage	Batch ID	Status	When
creating	Elicitation	`batch_69d8b918221c8190a9f7b563d64ac677`	completed	April 10, 2026, 8:47 a.m.
NER	Named-entity recognition	`batch_69e51750d3dc8190b153046c1171ee2b`	completed	April 19, 2026, 5:56 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a03d7764a84819095e35108a71f8e96`	completed	May 13, 2026, 1:44 a.m.
NEDg	Description generation	`batch_6a03de5ba068819080dfdf66ba03eb5c`	completed	May 13, 2026, 2:13 a.m.
NED2	Entity disambiguation (via description)	`batch_6a03defaf90c81908348ebd286de0e32`	completed	May 13, 2026, 2:16 a.m.

Created at: April 10, 2026, 10:38 a.m.