Triple

T12216307
Position Surface form Disambiguated ID Type / Status
Subject James Cobb E291093 entity
Predicate sibling P363 FINISHED
Object Philippa Cobb E352993 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: Philippa Cobb | Statement: [James Cobb, sibling, Philippa Cobb]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Philippa Cobb
Context triple: [James Cobb, sibling, Philippa Cobb]
  • A. Philippa Cobb chosen
    Philippa Cobb is the young daughter of Dom Cobb in the film "Inception."
  • B. Philippa Braithwaite
    Philippa Braithwaite is a British television producer known for her work on series such as "Doc Martin" and for being married to actor Martin Clunes.
  • C. Rosemary Forsyth
    Rosemary Forsyth is a Canadian-born American actress best known for her roles in 1960s and 1970s films and television dramas.
  • D. Philippa Price
    Philippa Price is a British visual artist and director known for her surreal, high-concept music videos and fashion films for major pop and R&B artists.
  • E. Cath Hardacre
    Cath Hardacre is the central protagonist of the British medical drama series "Trust Me," a skilled nurse who assumes a false identity as a doctor to rebuild her life and career.
  • 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_69d6ab65923081909acfc61b7a612233 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91c9419d48190b0037fe8edc681c4 completed April 10, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f64b873c308190a2c1d02723cfa2e9 completed May 2, 2026, 7:07 p.m.
Created at: April 8, 2026, 9:51 p.m.