Triple

T9886199
Position Surface form Disambiguated ID Type / Status
Subject Martin Crane E180936 entity
Predicate closeRelationshipWith P14992 FINISHED
Object Daphne Moon E175665 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: Daphne Moon | Statement: [Martin Crane, closeRelationshipWith, Daphne Moon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Daphne Moon
Context triple: [Martin Crane, closeRelationshipWith, Daphne Moon]
  • A. Daphne Moon chosen
    Daphne Moon is a quirky, psychic-leaning live-in physical therapist and housekeeper who becomes a central member of the Crane household on the television sitcom "Frasier."
  • B. Joan Blackman
    Joan Blackman is an American actress best known for her leading roles opposite Elvis Presley in early 1960s films.
  • C. Daphne Keen
    Daphne Keen is a British-Spanish actress best known for her breakout role as Laura/X-23 in the film "Logan" and as Lyra Belacqua in the television series "His Dark Materials."
  • D. Dani Dennison
    Dani Dennison is a brave and spirited young girl in the film "Hocus Pocus" who helps her brother battle resurrected witches on Halloween night.
  • E. Sarah Linden
    Sarah Linden is the introspective, relentless homicide detective at the center of the American crime drama series "The Killing."
  • 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_69ca828082cc8190a40f8d299caa6545 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cdb45659748190a3ebd1abe23c8779 completed April 2, 2026, 12:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69d20d7cc8e481909efdd1333ae740a3 completed April 5, 2026, 7:21 a.m.
Created at: March 30, 2026, 8:38 p.m.