Triple

T9548857
Position Surface form Disambiguated ID Type / Status
Subject Melanie Lynskey E230366 entity
Predicate televisionSeriesAppearance P57975 FINISHED
Object Castle Rock E103959 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: Castle Rock | Statement: [Melanie Lynskey, televisionSeriesAppearance, Castle Rock]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Castle Rock
Context triple: [Melanie Lynskey, televisionSeriesAppearance, Castle Rock]
  • A. Castle Rock
    Castle Rock is the prominent volcanic crag in Edinburgh that forms the dramatic natural foundation of Edinburgh Castle.
  • B. Castle Rock
    Castle Rock is a prominent sandstone outcrop in Nottingham, England, historically significant as the elevated site on which Nottingham Castle was built.
  • C. Castle Rock
    Castle Rock is a rapidly growing commuter town in central Colorado known for its distinctive castle-shaped butte and family-oriented suburban character between Denver and Colorado Springs.
  • D. Castle Rock chosen
    Castle Rock is a psychological horror television series inspired by the interconnected universe of Stephen King’s stories, released as an original program on Hulu.
  • E. Castle Rock, Maine
    Castle Rock, Maine is a fictional small town in Stephen King’s works, known as the setting for many of his horror and suspense stories.
  • 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_69ca847c70b8819088a0a0bad64a50d6 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd99059138819088ae54b26df979cf completed April 1, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1528068a481908d5c8037b4591db5 completed April 4, 2026, 6:03 p.m.
Created at: March 30, 2026, 8:02 p.m.