Triple

T23629001

Position	Surface form	Disambiguated ID	Type / Status
Subject	M. A. R. Barker	`E583552`	entity
Predicate	settingLanguageCreated	`P56530`	FINISHED
Object	Tsolyáni Tsolyáni is a richly developed fictional language created by M. A. R. Barker for his Tekumel fantasy setting, featuring complex grammar and an extensive constructed culture.	`E1593160`	NE FINISHED

How this triple was built (3 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: Tsolyáni | Statement: [M. A. R. Barker, settingLanguageCreated, Tsolyáni]

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: Tsolyáni
Triple: [M. A. R. Barker, settingLanguageCreated, Tsolyáni]

Generated description

Tsolyáni is a richly developed fictional language created by M. A. R. Barker for his Tekumel fantasy setting, featuring complex grammar and an extensive constructed culture.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: settingLanguageCreated
Context triple: [M. A. R. Barker, settingLanguageCreated, Tsolyáni]

A. createdInLanguage chosen
Indicates that something was produced, authored, or developed using a particular language (natural or programming).
B. adoptedLanguage
Indicates that an entity has chosen and begun using a particular language, typically as its official, primary, or preferred means of communication.
C. requiredLanguage
Indicates that a specific language is necessary or must be used for a given entity, action, or interaction.
D. navigationLanguage
Indicates the language used for navigation-related content, such as menus, directions, or interface controls.
E. targetLanguage
Indicates the language that is the intended recipient or focus of a communication, translation, or linguistic operation.
F. None of above.

Provenance (6 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_69e248fc8d74819091bd5baef2f36f6f`	completed	April 17, 2026, 2:51 p.m.
NER	Named-entity recognition	`batch_69f1b1e5ae80819085c417e8d81b74ad`	completed	April 29, 2026, 7:23 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a0f459eb53081908a35c47da2c9680a`	completed	May 21, 2026, 5:49 p.m.
NEDg	Description generation	`batch_6a0f468e0fb88190b3dc9ee15309dea1`	completed	May 21, 2026, 5:53 p.m.
NED2	Entity disambiguation (via description)	`batch_6a0f47974f7c819088de0827ae15dd61`	completed	May 21, 2026, 5:57 p.m.
PD	Predicate disambiguation	`batch_69f118d0e0588190a86527a7747c5427`	completed	April 28, 2026, 8:30 p.m.

Created at: April 17, 2026, 6:46 p.m.