Triple

T10589019
Position Surface form Disambiguated ID Type / Status
Subject Lord Cutler Beckett E249932 entity
Predicate enemyOf P437 FINISHED
Object Jack Sparrow E102774 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: Jack Sparrow | Statement: [Lord Cutler Beckett, enemyOf, Jack Sparrow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jack Sparrow
Context triple: [Lord Cutler Beckett, enemyOf, Jack Sparrow]
  • A. Captain Jack Sparrow chosen
    Captain Jack Sparrow is the eccentric, cunning pirate captain and central antihero of Disney’s Pirates of the Caribbean film series.
  • B. Captain Jack
    Captain Jack was the Modoc leader who commanded his people during the Modoc War against United States forces in the 1870s.
  • C. Captain Jack
    Captain Jack is the charismatic, time-traveling former Time Agent and leader of Torchwood from the Doctor Who universe.
  • D. Will Turner
    Will Turner is a skilled blacksmith-turned-pirate and the noble, determined hero of the Pirates of the Caribbean film series.
  • E. Hector Barbossa
    Hector Barbossa is a cunning and morally ambiguous pirate captain from the Pirates of the Caribbean film series, known for his shifting alliances, sharp wit, and rivalry-turned-partnership with Jack Sparrow.
  • 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_69d381c9d3d48190a29ee491e1696a0e completed April 6, 2026, 9:50 a.m.
NER Named-entity recognition batch_69d5277a39f08190848f24752cfa4b8f completed April 7, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69d94b9440548190bff01847a940266b completed April 10, 2026, 7:12 p.m.
Created at: April 6, 2026, 12:40 p.m.