Triple

T11312016
Position Surface form Disambiguated ID Type / Status
Subject Gillingham, Kent E267858 entity
Predicate nearbyMilitarySite P19544 FINISHED
Object Fort Amherst E499397 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 Amherst | Statement: [Gillingham, Kent, nearbyMilitarySite, Fort Amherst]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fort Amherst
Context triple: [Gillingham, Kent, nearbyMilitarySite, Fort Amherst]
  • A. Fort Amherst chosen
    Fort Amherst is a historic 18th-century artillery fort and defensive complex in Chatham, Kent, that played a key role in protecting the Royal Dockyard and the River Medway.
  • B. Fort Amherst
    Fort Amherst is a historic coastal defense site and lighthouse complex guarding the entrance to St. John’s Harbour in Newfoundland and Labrador, Canada.
  • C. Fort Pembroke
    Fort Pembroke is a 19th-century British coastal fortification in Malta that was built to defend the approaches to Marsamxett Harbour and the surrounding area.
  • D. Fort Marlborough
    Fort Marlborough is a historic British colonial fortress in Bengkulu, Indonesia, known for its well-preserved architecture and role in the region’s colonial history.
  • E. Fort Putnam
    Fort Putnam is a historic Revolutionary War-era fortification overlooking the Hudson River at West Point, New York, now preserved as part of the United States Military Academy’s historic district.
  • 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_69d6aaca5c24819083db46a30d86cb34 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e9c1b7dc81908d8cc768c47390d3 completed April 9, 2026, 6:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69e50a7fc06881909afe85a600d25ff2 completed April 19, 2026, 5:01 p.m.
Created at: April 8, 2026, 9:32 p.m.