Triple

T14664571
Position Surface form Disambiguated ID Type / Status
Subject Margaret Cavendish-Harley E344333 entity
Predicate familyName P18 FINISHED
Object Harley E644573 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: Harley | Statement: [Margaret Cavendish-Harley, familyName, Harley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harley
Context triple: [Margaret Cavendish-Harley, familyName, Harley]
  • A. Harley
    Harley is the central protagonist of Tyler Perry’s film "Temptation: Confessions of a Marriage Counselor," whose personal and marital struggles drive the story’s exploration of infidelity and its consequences.
  • B. Harley chosen
    Harley is an English surname historically associated with prominent political figures such as Robert Harley, 1st Earl of Oxford and Earl Mortimer.
  • C. Harley
    Harley is the given name of the English actor, director, and playwright Granville Barker, a key figure in early 20th-century British theatre.
  • D. Harley
    Harley is the middle name of Henry "Hap" Arnold, a pioneering American air commander and General of the Air Force during World War II.
  • E. Harley
    Harley is a troubled young heroin addict whose tumultuous relationship and self-destructive behavior drive the narrative of the film "Heaven Knows What."
  • 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_69d822e283fc8190a0e4c235cf880052 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb54ae5ac81908cc69891f280e5f7 completed April 14, 2026, 9:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdd5e4789481909a64622a1d284373 completed May 8, 2026, 12:24 p.m.
Created at: April 10, 2026, 1:27 a.m.