Triple

T30543310
Position Surface form Disambiguated ID Type / Status
Subject John Paulding E777339 entity
Predicate coCaptors P169840 FINISHED
Object Isaac Van Wart
Isaac Van Wart was an American militiaman during the Revolutionary War, best known as one of the three captors of British Major John André, helping to expose Benedict Arnold’s treason.
 E1929537 NE FINISHED

How this triple was built (3 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: Isaac Van Wart | Statement: [John Paulding, coCaptors, Isaac Van Wart]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Isaac Van Wart
Triple: [John Paulding, coCaptors, Isaac Van Wart]
Generated description
Isaac Van Wart was an American militiaman during the Revolutionary War, best known as one of the three captors of British Major John André, helping to expose Benedict Arnold’s treason.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: coCaptors
Context triple: [John Paulding, coCaptors, Isaac Van Wart]
  • A. designedToCapture
    Indicates that one entity was intentionally created or configured for the purpose of recording, containing, or acquiring another entity or a specific type of target.
  • B. capturedBy
    Indicates that one entity has been seized, taken into control, or otherwise apprehended by another entity.
  • C. capturedFor
    Indicates that one entity has been taken into custody, control, or possession specifically for the benefit, use, or purpose of another entity.
  • D. capturedUsing
    Indicates that something was recorded, obtained, or documented by means of a specified tool, method, or device.
  • E. capturedIn
    Indicates that one entity was taken prisoner, seized, or otherwise brought under control within the context, location, or event represented by another entity.
  • F. None of above. chosen

Provenance (7 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_69f2249d183c8190b79937c1768d2163 completed April 29, 2026, 3:32 p.m.
NER Named-entity recognition batch_69f6888dfcd881908d977b84bce63d9c completed May 2, 2026, 11:28 p.m.
NED1 Entity disambiguation (via context triple) batch_6a2898c1cedc819091a200a48cdba8e6 completed June 9, 2026, 10:50 p.m.
NEDg Description generation batch_6a2899be081c8190ba9cd748063e8dc0 completed June 9, 2026, 10:54 p.m.
NED2 Entity disambiguation (via description) batch_6a289ad47e94819094f1ea64c2804aa2 completed June 9, 2026, 10:59 p.m.
PD Predicate disambiguation batch_69f67e42d6688190b60e91d2c388c555 completed May 2, 2026, 10:44 p.m.
PDg Predicate description generation batch_69f6827a7b9c8190ab13605aacc81df9 completed May 2, 2026, 11:02 p.m.
Created at: April 29, 2026, 8:19 p.m.