Triple

T17876017
Position Surface form Disambiguated ID Type / Status
Subject Hannah Waterman E446954 entity
Predicate familyName P18 FINISHED
Object Waterman NE NERFINISHED

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: Waterman | Statement: [Hannah Waterman, familyName, Waterman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Waterman
Context triple: [Hannah Waterman, familyName, Waterman]
  • A. Waterman chosen
    Waterman is a historic luxury pen and writing instruments brand known for its high-quality fountain pens and elegant design.
  • B. The Water Man
    The Water Man is a 2020 family adventure-drama film and the directorial debut of David Oyelowo, following a boy’s mystical quest to save his ailing mother.
  • C. The Boat
    The Boat is a notable work associated with Joe Roberts, recognized for its creative and artistic significance.
  • D. The Boat
    The Boat is a renowned painting by Catalan modernist artist Ramon Casas, exemplifying his atmospheric style and interest in contemporary life.
  • E. Opperman
    Opperman is a surname shared by various notable individuals across fields such as literature, politics, and sports.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9f4c22c819093c2680434472894 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49aa614b48190bdc9e905e9e6d5e0 completed April 19, 2026, 9:04 a.m.
Created at: April 10, 2026, 10:18 a.m.