Triple

T5843203
Position Surface form Disambiguated ID Type / Status
Subject Crystal Langhorne E129642 entity
Predicate familyName P18 FINISHED
Object Langhorne E129642 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: Langhorne | Statement: [Crystal Langhorne, familyName, Langhorne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Langhorne
Context triple: [Crystal Langhorne, familyName, Langhorne]
  • A. Langhorne
    Langhorne is the middle name of Samuel Langhorne Clemens, better known by his pen name Mark Twain, the famed American author and humorist.
  • B. Langhorne chosen
    Langhorne is a surname most notably associated with Crystal Langhorne, an American professional basketball player who starred in the WNBA.
  • C. Bala Cynwyd
    Bala Cynwyd is a suburban community on Philadelphia’s Main Line in Lower Merion Township, Pennsylvania, known for its residential neighborhoods and proximity to the city.
  • D. Jenkintown
    Jenkintown is a suburban borough just north of Philadelphia known as a key regional rail hub and residential community.
  • E. Glen Mills
    Glen Mills is a renowned Jamaican sprint coach best known for guiding Usain Bolt to multiple world records and Olympic titles.
  • 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_69c0084bd31c8190a796bb6284845e83 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c034d9da0c8190970319d0dc2fc73f completed March 22, 2026, 6:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0a1a6587c8190b76b1005178c29a9 completed March 23, 2026, 2:12 a.m.
Created at: March 22, 2026, 3:54 p.m.