Triple

T33888991
Position Surface form Disambiguated ID Type / Status
Subject Siege of Fort Pulaski E868705 entity
Predicate reasonForSurrender P128787 FINISHED
Object breach threatened Fort Pulaski’s powder magazine LITERAL 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: breach threatened Fort Pulaski’s powder magazine | Statement: [Siege of Fort Pulaski, reasonForSurrender, breach threatened Fort Pulaski’s powder magazine]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: reasonForSurrender
Context triple: [Siege of Fort Pulaski, reasonForSurrender, breach threatened Fort Pulaski’s powder magazine]
  • A. causeOfSurrender chosen
    Indicates the factor, event, or condition that led directly to an entity’s surrender.
  • B. reasonForForfeiture
    Indicates the cause or justification that led to something being surrendered, lost, or taken away.
  • C. typeOfSurrender
    Indicates the specific manner or category of surrender that characterizes how one party yields or gives up to another.
  • D. reasonForRenunciation
    Indicates the specific cause, motive, or circumstance that led an entity to renounce or give up something.
  • E. resultOfSurrender
    Indicates that something exists or occurs as a consequence or outcome of a surrender event or act of capitulation.
  • F. None of above.

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_69f34996761c8190864e42f7c9cf215b completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69fd783fed9c81909e792702636c4f1f completed May 8, 2026, 5:44 a.m.
PD Predicate disambiguation batch_69fd7788e63c81909de22fdafcfe41c0 completed May 8, 2026, 5:41 a.m.
Created at: May 1, 2026, 1:48 a.m.