Triple

T24616288
Position Surface form Disambiguated ID Type / Status
Subject Roy Cooper E609268 entity
Predicate precededBy P97 FINISHED
Object Pat McCrory as Governor of North Carolina
Pat McCrory served as the Republican governor of North Carolina in the early 2010s, known for his conservative policies and controversial legislation on issues such as voting rights and transgender bathroom access.
E79895 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: Pat McCrory as Governor of North Carolina | Statement: [Roy Cooper, precededBy, Pat McCrory as Governor of North Carolina]
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: Pat McCrory as Governor of North Carolina
Triple: [Roy Cooper, precededBy, Pat McCrory as Governor of North Carolina]
Generated description
Pat McCrory served as the Republican governor of North Carolina in the early 2010s, known for his conservative policies and controversial legislation on issues such as voting rights and transgender bathroom access.

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_69e2c4d1140081909c58667bf68f80c3 completed April 17, 2026, 11:40 p.m.
NER Named-entity recognition batch_69f2aa62574c81908d72e4db088cace4 completed April 30, 2026, 1:03 a.m.
NED1 Entity disambiguation (via context triple) batch_6a10047d863c8190b7ebbd9053e2ff5a completed May 22, 2026, 7:23 a.m.
NEDg Description generation batch_6a100734702c8190ad66dfa3eace6c00 completed May 22, 2026, 7:35 a.m.
NED2 Entity disambiguation (via description) batch_6a1007bfa1c88190ab8b4199b84a4db0 completed May 22, 2026, 7:37 a.m.
Created at: April 18, 2026, 2:31 a.m.