Triple

T9184283
Position Surface form Disambiguated ID Type / Status
Subject Andrew Martin E220414 entity
Predicate firstOwner P32021 FINISHED
Object Gerald Martin
Gerald Martin is a person known primarily in relation to Andrew Martin, likely as a family member or close associate.
 E783087 NE FINISHED

How this triple was built (4 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: Gerald Martin | Statement: [Andrew Martin, firstOwner, Gerald Martin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gerald Martin
Context triple: [Andrew Martin, firstOwner, Gerald Martin]
  • A. Gerald Crich
    Gerald Crich is a wealthy, conflicted industrialist and one of the central male characters in D. H. Lawrence’s novel "Women in Love."
  • B. Gerald Austin
    Gerald Austin is a former National Football League official best known for serving as the referee in multiple Super Bowls, including Super Bowl XXXV.
  • C. John Bluthal
    John Bluthal was a Polish-born British actor best known for his comic roles in British television and film, including his memorable performance in the sitcom "The Vicar of Dibley."
  • D. Gerard Brown
    Gerard Brown is a screenwriter best known for co-writing the 1992 crime drama film "Juice."
  • E. John Dolman
    John Dolman was an English clergyman and benefactor of the late 16th century best known for establishing Pocklington School in Yorkshire.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Gerald Martin
Triple: [Andrew Martin, firstOwner, Gerald Martin]
Generated description
Gerald Martin is a person known primarily in relation to Andrew Martin, likely as a family member or close associate.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gerald Martin
Target entity description: Gerald Martin is a person known primarily in relation to Andrew Martin, likely as a family member or close associate.
  • A. Gerald Crich
    Gerald Crich is a wealthy, conflicted industrialist and one of the central male characters in D. H. Lawrence’s novel "Women in Love."
  • B. Gerald Austin
    Gerald Austin is a former National Football League official best known for serving as the referee in multiple Super Bowls, including Super Bowl XXXV.
  • C. John Bluthal
    John Bluthal was a Polish-born British actor best known for his comic roles in British television and film, including his memorable performance in the sitcom "The Vicar of Dibley."
  • D. Gerard Brown
    Gerard Brown is a screenwriter best known for co-writing the 1992 crime drama film "Juice."
  • E. John Dolman
    John Dolman was an English clergyman and benefactor of the late 16th century best known for establishing Pocklington School in Yorkshire.
  • F. None of above. chosen

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_69ca83e6d77c81909862b7afef56b1bf completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccc31734908190b8ebe3b57849ca5f completed April 1, 2026, 7:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69d05c1474a08190aa3e3e90326a20d1 completed April 4, 2026, 12:32 a.m.
NEDg Description generation batch_69d05ca2a3f881909ed9193560b5b0cd completed April 4, 2026, 12:34 a.m.
NED2 Entity disambiguation (via description) batch_69d05d4191f8819083c0ae2a68059c93 completed April 4, 2026, 12:37 a.m.
Created at: March 30, 2026, 7:24 p.m.