Triple

T18098448
Position Surface form Disambiguated ID Type / Status
Subject City of Mobile E433149 entity
Predicate hasLandmark P105 FINISHED
Object Fort Conde 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: Fort Conde | Statement: [City of Mobile, hasLandmark, Fort Conde]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fort Conde
Context triple: [City of Mobile, hasLandmark, Fort Conde]
  • A. Fort Conde chosen
    Fort Conde is a reconstructed 18th-century French colonial fort and museum in Mobile, Alabama, that interprets the region’s early military and colonial history.
  • B. Fort de Salettes
    Fort de Salettes is a historic mountain fortification near Briançon in the French Alps, built as part of the town’s defensive system and now recognized as part of a UNESCO World Heritage site.
  • C. Fort l’Écluse
    Fort l’Écluse is a historic fortified stronghold in eastern France that once controlled access through the Rhône valley and the Jura mountains.
  • D. Fort d'Hœdic
    Fort d'Hœdic is a historic coastal fortification on the small island of Hœdic in Brittany, France, built to defend the surrounding maritime approaches.
  • E. Fort Tigné
    Fort Tigné is a late 18th-century polygonal coastal fortification in Malta, built by the Knights of St John to guard the entrance to Marsamxett Harbour.
  • 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_69d8b90916008190a1f110bd7ced5473 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4ddb3ef548190a322f98917b54a59 completed April 19, 2026, 1:50 p.m.
Created at: April 10, 2026, 10:27 a.m.