Triple

T20063470
Position Surface form Disambiguated ID Type / Status
Subject Essie Davis E499545 entity
Predicate familyName P18 FINISHED
Object Davis 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: Davis | Statement: [Essie Davis, familyName, Davis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Davis
Context triple: [Essie Davis, familyName, Davis]
  • A. Davis
    Davis is an underground rapid transit station in Somerville, Massachusetts, on Boston’s MBTA Red Line.
  • B. Davis
    Davis is the individual or party who served as the respondent in the U.S. Supreme Court case Steward Machine Co. v. Davis, which addressed the constitutionality of certain New Deal-era federal taxation and social welfare provisions.
  • C. Davis chosen
    Davis is a common English-language surname of Scottish and Welsh origin, often meaning "son of David."
  • D. Davis
    Davis is a small Northern California city known for hosting the University of California, Davis and for its strong emphasis on education, agriculture, and bicycle-friendly urban planning.
  • E. Davis
    Davis is a Chicago Transit Authority 'L' station on the Purple Line serving downtown Evanston, Illinois.
  • 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_69da6276bcf48190aabbf279192a5fb4 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66377b6b48190a0a37279f285123e completed April 20, 2026, 5:33 p.m.
Created at: April 11, 2026, 3:39 p.m.