Triple

T29729490
Position Surface form Disambiguated ID Type / Status
Subject Gillette Castle State Park E752278 entity
Predicate hasPart P35 FINISHED
Object Gillette Castle
Gillette Castle is a distinctive medieval-style stone mansion in East Haddam, Connecticut, built by actor William Gillette and now a popular historic landmark.
E1947446 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: Gillette Castle | Statement: [Gillette Castle State Park, hasPart, Gillette Castle]
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: Gillette Castle
Triple: [Gillette Castle State Park, hasPart, Gillette Castle]
Generated description
Gillette Castle is a distinctive medieval-style stone mansion in East Haddam, Connecticut, built by actor William Gillette and now a popular historic landmark.

Provenance (5 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_69f0d62a36a88190bf860f00da433ff8 completed April 28, 2026, 3:45 p.m.
NER Named-entity recognition batch_69f6732fff7c81908326c2deaffcdf86 completed May 2, 2026, 9:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a293885231c81909ccb06d9b7ca0936 completed June 10, 2026, 10:12 a.m.
NEDg Description generation batch_6a293c5b87988190b513ee94f24d0d1c completed June 10, 2026, 10:28 a.m.
NED2 Entity disambiguation (via description) batch_6a293cba99c08190b22b2ffd9cd76ec1 completed June 10, 2026, 10:30 a.m.
Created at: April 28, 2026, 7:41 p.m.