Triple

T16130613
Position Surface form Disambiguated ID Type / Status
Subject Mary Haas E391384 entity
Predicate notableStudent P4838 FINISHED
Object Charles Hockett E1123316 NE FINISHED

How this triple was built (2 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: Charles Hockett | Statement: [Mary Haas, notableStudent, Charles Hockett]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charles Hockett
Context triple: [Mary Haas, notableStudent, Charles Hockett]
  • A. Larry Hockett
    Larry Hockett is the fictional pitching coach character portrayed by Robert Wuhl in the baseball film "Bull Durham."
  • B. Charles F. Hockett chosen
    Charles F. Hockett was an American linguist best known for his work in structural linguistics and his influential formulation of the "design features" of human language.
  • C. William C. Stokoe
    William C. Stokoe was a pioneering American linguist whose groundbreaking work established American Sign Language as a legitimate, fully structured natural language.
  • D. A. C. Gimson
    A. C. Gimson was a prominent British phonetician and linguist best known for his influential work on the description and standardization of British pronunciation and for succeeding Daniel Jones at University College London.
  • E. Paul Kiparsky
    Paul Kiparsky is a prominent linguist known for his influential work in generative phonology and historical linguistics.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d87f1bb0988190b490d273dbf3fd03 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e2020829e88190b51ab32d22cf0259 completed April 17, 2026, 9:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff2aff07c8190bf693f652e2a2808 completed May 10, 2026, 2:51 a.m.
Created at: April 10, 2026, 5:01 a.m.