Triple

T13108917
Position Surface form Disambiguated ID Type / Status
Subject Tigerland E310919 entity
Predicate setting P1957 FINISHED
Object Fort Polk E608179 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 Polk | Statement: [Tigerland, setting, Fort Polk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fort Polk
Context triple: [Tigerland, setting, Fort Polk]
  • A. Fort Polk chosen
    Fort Polk is a major U.S. Army installation in Louisiana known primarily as a training center for combat readiness and large-scale field exercises.
  • B. Fort St. Philip
    Fort St. Philip is a historic coastal fortification in Louisiana that played a key defensive role in multiple American conflicts, including the War of 1812 and the Civil War.
  • C. Fort St. Philip
    Fort St. Philip was a strategically vital British-held fortress on the island of Menorca that played a central role in Mediterranean naval conflicts, including the Battle of Minorca in 1756.
  • D. Fort Plaisance
    Fort Plaisance was a French colonial fortification built to protect the fishing settlement at Placentia in what is now Newfoundland and Labrador, Canada.
  • E. Fort Rouillé
    Fort Rouillé was an 18th-century French trading post and military fortification located in what is now Toronto, Canada, built to support the fur trade and assert French presence in the region.
  • 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_69d806a872d08190a329806f8ff30df4 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d9817ce07881909ec552bf861ac175 completed April 10, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6e27bd8fc8190a81130b7cb3a8bd8 completed May 3, 2026, 5:51 a.m.
Created at: April 9, 2026, 9:05 p.m.