Triple

T30826780
Position Surface form Disambiguated ID Type / Status
Subject Rockwood Hall E785091 entity
Predicate hasParkArea P30832 FINISHED
Object Rockwood Hall State Park
Rockwood Hall State Park is a scenic New York state park along the Hudson River featuring open lawns, wooded trails, and historic estate grounds.
 E1970296 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: Rockwood Hall State Park | Statement: [Rockwood Hall, hasParkArea, Rockwood Hall State Park]
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: Rockwood Hall State Park
Triple: [Rockwood Hall, hasParkArea, Rockwood Hall State Park]
Generated description
Rockwood Hall State Park is a scenic New York state park along the Hudson River featuring open lawns, wooded trails, and historic estate grounds.

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_69f224b6642481909e8d701de2cd1a53 completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f690f72a188190a10fc7c5d88d803b completed May 3, 2026, 12:04 a.m.
NED1 Entity disambiguation (via context triple) batch_6a2b56146bf881909887ed354944ad49 completed June 12, 2026, 12:43 a.m.
NEDg Description generation batch_6a2b57d50afc8190ba50f7a268bc9420 completed June 12, 2026, 12:50 a.m.
NED2 Entity disambiguation (via description) batch_6a2b7126b9ec81909737cbb860bdb2c2 completed June 12, 2026, 2:38 a.m.
Created at: April 29, 2026, 8:44 p.m.