Triple

T15045412
Position Surface form Disambiguated ID Type / Status
Subject Disclosure E379213 entity
Predicate notableWork P4 FINISHED
Object Latch E379200 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: Latch | Statement: [Disclosure, notableWork, Latch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Latch
Context triple: [Disclosure, notableWork, Latch]
  • A. Latch chosen
    "Latch" is a 2012 breakout electronic soul single by Disclosure featuring Sam Smith, widely credited with launching Smith’s career and popularizing Disclosure’s signature sound.
  • B. Lock
    Lock is a Symfony component that provides a robust locking mechanism to prevent concurrent access conflicts in shared resources.
  • C. Locking Piece
    Locking Piece is a large abstract bronze sculpture by British artist Henry Moore, characterized by interlocking organic forms that explore balance, tension, and spatial relationships.
  • D. Locks
    "Locks" is a short story by Neil Gaiman, featured in his collection *Fragile Things*, that intertwines a retelling of "Goldilocks and the Three Bears" with reflections on parenthood and storytelling.
  • E. Ware Lock
    Ware Lock is a canal lock on the River Lee Navigation in Hertfordshire, England, used to raise and lower boats between different water levels.
  • 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_69d85cd64d108190853797a95c11cc45 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded830c3c08190a87b81abbbb75377 completed April 15, 2026, 12:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9de54380819084568664b63322d2 completed May 9, 2026, 2:37 a.m.
Created at: April 10, 2026, 3 a.m.