Triple

T14969665
Position Surface form Disambiguated ID Type / Status
Subject Marion Marshall E373282 entity
Predicate notableWork P4 FINISHED
Object Sailor Beware E958730 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: Sailor Beware | Statement: [Marion Marshall, notableWork, Sailor Beware]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sailor Beware
Context triple: [Marion Marshall, notableWork, Sailor Beware]
  • A. Sailor Beware chosen
    Sailor Beware is a 1952 American comedy film featuring the popular comic duo Dean Martin and Jerry Lewis in a Navy-themed romp.
  • B. Sailor Beware!
    Sailor Beware! is a popular mid-20th-century British stage comedy best known for its humorous portrayal of working-class life and romantic entanglements.
  • C. Fancy Sailor
    Fancy Sailor is a traditional Trinidad and Tobago Carnival masquerade character known for its exaggerated naval costume, comic swagger, and playful, theatrical movements.
  • D. Sailor on Horseback
    Sailor on Horseback is a biographical novel by Irving Stone about the life and struggles of American author Jack London.
  • E. Sail Out
    Sail Out is Jhené Aiko’s debut EP, a critically acclaimed R&B project that helped establish her introspective, atmospheric musical style.
  • 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_69d85ccbbcd48190acb56e7cf104d8ad completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded6e59a7c8190a1634a706ea68fda completed April 15, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe8be6ce68819099f841d83c6ca33d completed May 9, 2026, 1:20 a.m.
Created at: April 10, 2026, 2:49 a.m.