Triple

T20068917
Position Surface form Disambiguated ID Type / Status
Subject Mark Liberman E499681 entity
Predicate hasAcademicAdvisor P167 FINISHED
Object Morris Halle NE NERFINISHED

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: Morris Halle | Statement: [Mark Liberman, hasAcademicAdvisor, Morris Halle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Morris Halle
Context triple: [Mark Liberman, hasAcademicAdvisor, Morris Halle]
  • A. Morris Halle chosen
    Morris Halle was a pioneering Latvian-American linguist and phonologist, best known for his foundational work in generative phonology and his long collaboration with Noam Chomsky at MIT.
  • B. Tan Hall
    Tan Hall is a major academic and research building associated with the College of Chemistry at the University of California, Berkeley.
  • C. Walter Morosco
    Walter Morosco was an American film producer active during Hollywood’s studio era, known for overseeing several notable mid-20th-century motion pictures.
  • D. Silverman Hall
    Silverman Hall is a prominent academic and administrative building that serves as a central facility of the University of Pennsylvania Law School.
  • E. Packard Music Hall
    Packard Music Hall is a historic performing arts venue in Warren, Ohio, known for hosting concerts, theatrical productions, and community events.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da627770948190997f486f9a2e370f completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e664365ad0819089103b00d1cf8c9f completed April 20, 2026, 5:36 p.m.
Created at: April 11, 2026, 3:39 p.m.