Triple

T6956009
Position Surface form Disambiguated ID Type / Status
Subject Robert Kirkman E161244 entity
Predicate familyName P18 FINISHED
Object Kirkman
Kirkman is a surname most prominently associated with Robert Kirkman, the American comic book writer and creator of "The Walking Dead."
 E630963 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: Kirkman | Statement: [Robert Kirkman, familyName, Kirkman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kirkman
Context triple: [Robert Kirkman, familyName, Kirkman]
  • A. Kohan
    Kohan is a surname most prominently associated with American television writer and producer Jenji Kohan, known for creating the series "Weeds" and "Orange Is the New Black."
  • B. Wick
    Wick is a village in South Gloucestershire, England, known for its rural character and location between Bristol and Bath.
  • C. Wick
    Wick is a small coastal town in the far north of Scotland, historically known as a fishing port and regional administrative center.
  • D. Reidy
    Reidy is the surname of Affonso Eduardo Reidy, a prominent Brazilian modernist architect known for influential public housing and cultural projects in Rio de Janeiro.
  • E. Hooperman
    Hooperman is an American television dramedy series from the late 1980s starring John Ritter as a San Francisco police inspector balancing his personal and professional life.
  • 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: Kirkman
Triple: [Robert Kirkman, familyName, Kirkman]
Generated description
Kirkman is a surname most prominently associated with Robert Kirkman, the American comic book writer and creator of "The Walking Dead."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kirkman
Target entity description: Kirkman is a surname most prominently associated with Robert Kirkman, the American comic book writer and creator of "The Walking Dead."
  • A. Kohan
    Kohan is a surname most prominently associated with American television writer and producer Jenji Kohan, known for creating the series "Weeds" and "Orange Is the New Black."
  • B. Wick
    Wick is a small coastal town in the far north of Scotland, historically known as a fishing port and regional administrative center.
  • C. Wick
    Wick is a village in South Gloucestershire, England, known for its rural character and location between Bristol and Bath.
  • D. Reidy
    Reidy is the surname of Affonso Eduardo Reidy, a prominent Brazilian modernist architect known for influential public housing and cultural projects in Rio de Janeiro.
  • E. Hooperman
    Hooperman is an American television dramedy series from the late 1980s starring John Ritter as a San Francisco police inspector balancing his personal and professional life.
  • 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_69c68852a9a0819097797e31d492e273 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6dacf8c8c8190a25dbacebeb4b66e completed March 27, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69c75888d48c81908a8dbd16d7591b55 completed March 28, 2026, 4:26 a.m.
NEDg Description generation batch_69c7596571a48190a8a04b9b24b5e4cb completed March 28, 2026, 4:30 a.m.
NED2 Entity disambiguation (via description) batch_69c75a57dc308190a691d3ae55cc39ef completed March 28, 2026, 4:34 a.m.
Created at: March 27, 2026, 2:29 p.m.