Triple

T14958491
Position Surface form Disambiguated ID Type / Status
Subject Thelma Harper E372996 entity
Predicate hasRelative P367 FINISHED
Object Carl Harper E1140431 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: Carl Harper | Statement: [Thelma Harper, hasRelative, Carl Harper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carl Harper
Context triple: [Thelma Harper, hasRelative, Carl Harper]
  • A. Carl Harper chosen
    Carl Harper is a fictional character appearing in the comedy sketch "The Family."
  • B. Darryl Harper
    Darryl Harper is a music producer best known for his co-production work on Jay-Z’s hit single "99 Problems."
  • C. Joe Harper
    Joe Harper is a minor character in Mark Twain's classic novel "The Adventures of Tom Sawyer," known as one of Tom's close friends and fellow mischief-makers in the fictional town of St. Petersburg.
  • D. Chris Harper
    Chris Harper is a theatre producer best known as the co-founder of the acclaimed London-based company Elliott & Harper Productions alongside director Marianne Elliott.
  • E. Adam Harper
    Adam Harper is a British mathematician known for his contributions to analytic number theory, particularly in the study of random multiplicative functions and the distribution of prime numbers.
  • 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_69d85cca979481908747d2a81eba1cea completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded6cd85bc81909040b7ff78f62554 completed April 15, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69fedd2046348190bcf8660bf3825b8f completed May 9, 2026, 7:07 a.m.
Created at: April 10, 2026, 2:40 a.m.