Triple

T9802085
Position Surface form Disambiguated ID Type / Status
Subject Sarah Palmer E237861 entity
Predicate hasRomanticRelationshipWith P9994 FINISHED
Object Tom Hanniger E270775 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: Tom Hanniger | Statement: [Sarah Palmer, hasRomanticRelationshipWith, Tom Hanniger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Hanniger
Context triple: [Sarah Palmer, hasRomanticRelationshipWith, Tom Hanniger]
  • A. Tom Hanniger chosen
    Tom Hanniger is the troubled miner and central figure of the slasher film "My Bloody Valentine 3D," whose dark past and possible connection to a series of brutal murders drive the movie’s suspense.
  • B. Ian Callaghan
    Ian Callaghan is a former English footballer best known for his long and record-breaking career with Liverpool FC, where he became the club’s all-time appearance holder and won numerous domestic and European titles.
  • C. Rob MacGregor
    Rob MacGregor is an American author best known for writing several Indiana Jones tie-in novels and works of adventure and speculative fiction.
  • D. Duncan Stewart
    Duncan Stewart is a music producer best known for his work on U2’s album "Songs of Surrender."
  • E. Alan McCulloch
    Alan McCulloch is a relatively obscure individual about whom no widely known public information is available.
  • 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_69ca84dd4608819097ff4ed00feca280 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda62b41048190bcef70a7591830c6 completed April 1, 2026, 11:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69d20d1b170881908954233f927457a0 completed April 5, 2026, 7:19 a.m.
Created at: March 30, 2026, 8:29 p.m.