Triple

T6184646
Position Surface form Disambiguated ID Type / Status
Subject Robert Blust E138026 entity
Predicate familyName P18 FINISHED
Object Blust
Blust is a surname most notably associated with Robert Blust, an influential American linguist known for his extensive work on Austronesian languages.
 E574293 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: Blust | Statement: [Robert Blust, familyName, Blust]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Blust
Context triple: [Robert Blust, familyName, Blust]
  • A. Flen
    Flen is a small Swedish town known as the administrative center of Flen Municipality in the province of Södermanland.
  • B. Boontling
    Boontling is a highly localized and inventive American English argot developed in the late 19th century in Boonville, California, known for its unique vocabulary and obscure origins.
  • C. Blix
    Blix is a 19th-century novel by American naturalist writer Frank Norris that follows a young woman’s coming-of-age and romantic experiences in San Francisco.
  • D. Blix
    Blix is a Swedish surname most notably associated with Hans Blix, the former head of the International Atomic Energy Agency and UN weapons inspector.
  • E. Fluberg
    Fluberg is a small village in Norway located near the shores of Randsfjorden, known for its rural landscape and lakeside setting.
  • 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: Blust
Triple: [Robert Blust, familyName, Blust]
Generated description
Blust is a surname most notably associated with Robert Blust, an influential American linguist known for his extensive work on Austronesian languages.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Blust
Target entity description: Blust is a surname most notably associated with Robert Blust, an influential American linguist known for his extensive work on Austronesian languages.
  • A. Flen
    Flen is a small Swedish town known as the administrative center of Flen Municipality in the province of Södermanland.
  • B. Boontling
    Boontling is a highly localized and inventive American English argot developed in the late 19th century in Boonville, California, known for its unique vocabulary and obscure origins.
  • C. Blix
    Blix is a Swedish surname most notably associated with Hans Blix, the former head of the International Atomic Energy Agency and UN weapons inspector.
  • D. Blix
    Blix is a 19th-century novel by American naturalist writer Frank Norris that follows a young woman’s coming-of-age and romantic experiences in San Francisco.
  • E. Fluberg
    Fluberg is a small village in Norway located near the shores of Randsfjorden, known for its rural landscape and lakeside setting.
  • 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_69c008a8fd408190b7ec6e42934974a6 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c061020d148190ae2edf2b363f1e24 completed March 22, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69c141c6b5888190983bff620c7663cc completed March 23, 2026, 1:36 p.m.
NEDg Description generation batch_69c1472997d081909266b0e64fdbfe96 completed March 23, 2026, 1:59 p.m.
NED2 Entity disambiguation (via description) batch_69c147b5214c819082c20480965842be completed March 23, 2026, 2:01 p.m.
Created at: March 22, 2026, 4:19 p.m.