Triple

T1520501
Position Surface form Disambiguated ID Type / Status
Subject Morris Halle E32214 entity
Predicate influenced P9 FINISHED
Object Paul Kiparsky E175546 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: Paul Kiparsky | Statement: [Morris Halle, influenced, Paul Kiparsky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Kiparsky
Context triple: [Morris Halle, influenced, Paul Kiparsky]
  • A. Paul Kiparsky chosen
    Paul Kiparsky is a prominent linguist known for his influential work in generative phonology and historical linguistics.
  • B. Michael Kenstowicz
    Michael Kenstowicz is an American linguist and phonologist known for his influential work on generative phonology and for co-authoring widely used textbooks in the field.
  • C. Robert Blust
    Robert Blust was an influential American linguist and Austronesian specialist known for his extensive comparative and historical work on the languages of the Pacific and Southeast Asia.
  • D. Norbert Hornstein
    Norbert Hornstein is an American linguist and syntactician known for his influential work in generative grammar and his advocacy of minimalist approaches to linguistic theory.
  • E. Joseph Greenberg
    Joseph Greenberg was an influential American linguist best known for his work on language classification and universals, including proposing major language families such as Nilo-Saharan.
  • 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_69a885e9b0ac819093a9806ad0efc82c completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a907f071848190a5fb8fa1b97ef4de completed March 5, 2026, 4:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad401616ec81908edd9dcb9f4a0184 completed March 8, 2026, 9:23 a.m.
Created at: March 4, 2026, 7:26 p.m.