Triple

T1489276
Position Surface form Disambiguated ID Type / Status
Subject Robert Fergusson E29538 entity
Predicate burialPlace P196 FINISHED
Object Canongate Kirkyard E30544 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: Canongate Kirkyard | Statement: [Robert Fergusson, burialPlace, Canongate Kirkyard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Canongate Kirkyard
Context triple: [Robert Fergusson, burialPlace, Canongate Kirkyard]
  • A. Canongate Kirkyard, Edinburgh chosen
    Canongate Kirkyard in Edinburgh is a historic churchyard on the Royal Mile, best known as the burial place of economist and philosopher Adam Smith.
  • B. Mount Kenton Cemetery
    Mount Kenton Cemetery is a burial ground in Paducah, Kentucky, best known as the final resting place of former U.S. Vice President Alben W. Barkley.
  • C. Anif Cemetery
    Anif Cemetery is the local burial ground serving the municipality of Anif in the Salzburg region of Austria.
  • D. Errancis Cemetery
    Errancis Cemetery was a former Parisian burial ground best known as the temporary resting place of many victims of the French Revolution, including Maximilien Robespierre.
  • E. Charlesgate
    Charlesgate is a major intersection and greenway area in Boston that links several key roadways and parklands near the Charles River.
  • 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_69a498da82e08190ba833330d05f380f completed March 1, 2026, 7:51 p.m.
NER Named-entity recognition batch_69a4c6a6095481909e9d406ac9a41828 completed March 1, 2026, 11:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad1ca7804c8190b6818ff344908028 completed March 8, 2026, 6:52 a.m.
Created at: March 1, 2026, 8:12 p.m.