Triple

T21539321
Position Surface form Disambiguated ID Type / Status
Subject Tor Wood E531438 entity
Predicate locatedNear P294 FINISHED
Object Torwood NE NERFINISHED

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: Torwood | Statement: [Tor Wood, locatedNear, Torwood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Torwood
Context triple: [Tor Wood, locatedNear, Torwood]
  • A. Torwood chosen
    Torwood is a small village in central Scotland, known for its historic castle ruins and nearby ancient woodland.
  • B. Ligertwood
    Ligertwood is a Scottish surname most notably borne by Alex Ligertwood, a singer and guitarist known for his work with the rock band Santana.
  • C. Toron
    Toron was a medieval lordship and fortress in the Crusader Kingdom of Jerusalem, located in what is now southern Lebanon.
  • D. Shandar
    Shandar was a French avant-garde record label known for releasing experimental and free jazz recordings in the 1970s.
  • E. Tanneron
    Tanneron is a commune in southeastern France’s Var department, known for its hilly landscapes and extensive mimosa forests overlooking the Mediterranean hinterland.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c45f17148190949c330ab9c27706 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee9d10a2888190bc4e502a829c76a4 completed April 26, 2026, 11:17 p.m.
Created at: April 16, 2026, 6:27 p.m.