Triple

T1584084
Position Surface form Disambiguated ID Type / Status
Subject Mobile, Alabama E34031 entity
Predicate hasLandmark P105 FINISHED
Object Fort Conde E98127 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: Fort Conde | Statement: [Mobile, Alabama, hasLandmark, Fort Conde]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fort Conde
Context triple: [Mobile, Alabama, 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 Vaux
    Fort Vaux is a French World War I fortress near Verdun, renowned for its fierce 1916 defense against German forces during the Battle of Verdun.
  • C. Fort du Portalet
    Fort du Portalet is a 19th-century French mountain fortress in the Pyrenees, later used as a prison during World War II, notably for detaining Marshal Philippe Pétain.
  • D. Fort Saint-Jean
    Fort Saint-Jean is a historic coastal fortress in Marseille, France, guarding the entrance to the Old Port and now integrated into the MuCEM museum complex.
  • E. Fort Fincastle
    Fort Fincastle is an 18th-century limestone fortress in Nassau, Bahamas, built to protect the harbor and now a popular historic landmark and tourist attraction.
  • 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_69a885fceb2c8190b47e0f7c0aefbff0 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a908f0e72c8190bb7a2a0c77379060 completed March 5, 2026, 4:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad4035dd7c8190817301c0a2b0b938 completed March 8, 2026, 9:24 a.m.
Created at: March 4, 2026, 7:27 p.m.