Triple

T15576913
Position Surface form Disambiguated ID Type / Status
Subject Marc Spector E374392 entity
Predicate alias P39 FINISHED
Object Jake Lockley E977052 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: Jake Lockley | Statement: [Marc Spector, alias, Jake Lockley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jake Lockley
Context triple: [Marc Spector, alias, Jake Lockley]
  • A. Jake Lockley chosen
    Jake Lockley is one of Moon Knight’s distinct personalities, typically portrayed as a streetwise cab driver persona that helps him gather information from the criminal underworld.
  • B. Tim Lockwood
    Tim Lockwood is the eccentric inventor father of protagonist Flint Lockwood in the animated film "Cloudy with a Chance of Meatballs."
  • C. John Loker
    John Loker is a British abstract painter known for his large-scale, gestural works that explore space, movement, and perception.
  • D. John Willock
    John Willock was a 16th-century Scottish reformer and theologian who played a significant role in the Scottish Reformation and helped shape its doctrinal foundations.
  • E. Guy Mountfort
    Guy Mountfort was a British advertising executive, author, and conservationist best known for co-founding the World Wildlife Fund and helping pioneer modern international wildlife conservation efforts.
  • 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_69d85ccd575081908909b71a3f3e3a61 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e22c89081909b1ec0cd36a1ef45 completed April 16, 2026, 2:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff56c3efb48190ad94d9d326c6c2c0 completed May 9, 2026, 3:46 p.m.
Created at: April 10, 2026, 4:11 a.m.