Triple

T28385027
Position Surface form Disambiguated ID Type / Status
Subject Dame Patsy Reddy E718996 entity
Predicate coLedReviewWith P164447 FINISHED
Object Sir Michael Cullen
Sir Michael Cullen was a prominent New Zealand politician and Labour Party finance minister known for his key role in shaping the country’s economic and social policy in the late 20th and early 21st centuries.
 E1820071 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: Sir Michael Cullen | Statement: [Dame Patsy Reddy, coLedReviewWith, Sir Michael Cullen]
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: Sir Michael Cullen
Triple: [Dame Patsy Reddy, coLedReviewWith, Sir Michael Cullen]
Generated description
Sir Michael Cullen was a prominent New Zealand politician and Labour Party finance minister known for his key role in shaping the country’s economic and social policy in the late 20th and early 21st centuries.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: coLedReviewWith
Context triple: [Dame Patsy Reddy, coLedReviewWith, Sir Michael Cullen]
  • A. coLedReviewOf chosen
    Indicates that two or more entities jointly led or were primarily responsible for conducting a review.
  • B. led
    Indicates that one entity guided, directed, or was in charge of another entity or activity, typically over a period of time.
  • C. ledSackOf
    Indicates that one entity directed or commanded the military attack or plundering raid against another entity.
  • D. reviewOf
    Indicates that one entity is a critical or evaluative assessment that is about or directed toward another entity.
  • E. luminescenceCapability
    Indicates the ability of an entity to emit light through luminescence.
  • F. None of above.

Provenance (6 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_69eff6ef211081909d31d9be5f5567e6 completed April 27, 2026, 11:53 p.m.
NER Named-entity recognition batch_69f64e37f7fc819083809149b6661e3c completed May 2, 2026, 7:19 p.m.
NED1 Entity disambiguation (via context triple) batch_6a164174c0348190bf2e295634e598fc completed May 27, 2026, 12:57 a.m.
NEDg Description generation batch_6a1641ff20fc819087e9e4e07ff41442 completed May 27, 2026, 12:59 a.m.
NED2 Entity disambiguation (via description) batch_6a16453193948190864ad3f56efe7866 completed May 27, 2026, 1:13 a.m.
PD Predicate disambiguation batch_69f64caede108190a35cc7cbfead866f completed May 2, 2026, 7:12 p.m.
Created at: April 28, 2026, 1:09 a.m.