Triple

T16333556
Position Surface form Disambiguated ID Type / Status
Subject Francine Jones E396616 entity
Predicate child P120 FINISHED
Object Tish Jones E400462 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: Tish Jones | Statement: [Francine Jones, child, Tish Jones]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tish Jones
Context triple: [Francine Jones, child, Tish Jones]
  • A. Tish Jones chosen
    Tish Jones is a supporting character in the Doctor Who universe, known as the ambitious and resourceful sister of Martha Jones.
  • B. Georgia Jones
    Georgia Jones is the central protagonist of the television series "Shake It Up," around whom the show's main storylines and character relationships revolve.
  • C. Francine Jones
    Francine Jones is a recurring character in the Doctor Who television series, best known as the mother of companion Martha Jones and for her involvement in the events surrounding the Master’s takeover of Earth.
  • D. Anney Jones
    Anney Jones is the daughter of professional wrestler AJ Styles.
  • E. Rachel Jones
    Rachel Jones is the woman after whom the small town of Rachel, Nevada—known for its proximity to Area 51—was named.
  • 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_69d87f255b788190a400eba031dd85d8 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2c4e1da1081909bec6e77e6109dce completed April 17, 2026, 11:40 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01232399008190b23dfaec237563ef completed May 11, 2026, 12:30 a.m.
Created at: April 10, 2026, 5:07 a.m.