Triple

T18541912
Position Surface form Disambiguated ID Type / Status
Subject Siuslaw E453120 entity
Predicate ISO639-3 P208 FINISHED
Object sis
sis is the ISO 639-3 language code for the Siuslaw language, an extinct Native American language once spoken in the coastal region of Oregon, USA.
E1331048 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: sis | Statement: [Siuslaw, ISO639-3, sis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: sis
Context triple: [Siuslaw, ISO639-3, sis]
  • A. SI
    SI is the post-nominal abbreviation used to denote recipients of Pakistan’s Sitara-e-Imtiaz, one of the country’s highest civilian honors.
  • B. SI
    SI is the globally accepted metric-based system of measurement used in science, industry, and everyday life.
  • C. SI
    SI is the vehicle registration code used on license plates for the German city of Siegen.
  • D. SI
    SI is the two-letter ISO 3166-1 alpha-2 country code for Slovenia, a Central European nation known for its mountains, lakes, and membership in the European Union.
  • E. SI
    SI is the abbreviation for Skeptical Inquirer, a magazine devoted to scientific skepticism, critical thinking, and the investigation of extraordinary claims.
  • 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: sis
Triple: [Siuslaw, ISO639-3, sis]
Generated description
sis is the ISO 639-3 language code for the Siuslaw language, an extinct Native American language once spoken in the coastal region of Oregon, USA.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: sis
Target entity description: sis is the ISO 639-3 language code for the Siuslaw language, an extinct Native American language once spoken in the coastal region of Oregon, USA.
  • A. SI
    SI is the post-nominal abbreviation used to denote recipients of Pakistan’s Sitara-e-Imtiaz, one of the country’s highest civilian honors.
  • B. SI
    SI is the vehicle registration code used on license plates for the German city of Siegen.
  • C. SI
    SI is the abbreviation for Skeptical Inquirer, a magazine devoted to scientific skepticism, critical thinking, and the investigation of extraordinary claims.
  • D. SI
    SI is the globally accepted metric-based system of measurement used in science, industry, and everyday life.
  • E. SI
    SI is the two-letter ISO 3166-1 alpha-2 country code for Slovenia, a Central European nation known for its mountains, lakes, and membership in the European Union.
  • 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_69d8d387b5548190aa030dad2cb4947e completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e534b749b88190ad03b26bee3c89df completed April 19, 2026, 8:01 p.m.
NED1 Entity disambiguation (via context triple) batch_6a049ad9d8108190b7251f293563a056 completed May 13, 2026, 3:38 p.m.
NEDg Description generation batch_6a049d1fabfc8190ade010ba5d2a2c1b completed May 13, 2026, 3:47 p.m.
NED2 Entity disambiguation (via description) batch_6a049f83689c81908e02646a157c80d4 completed May 13, 2026, 3:57 p.m.
Created at: April 10, 2026, 11:38 a.m.