Triple

T10845344
Position Surface form Disambiguated ID Type / Status
Subject In Her Skin E255995 entity
Predicate producer P490 FINISHED
Object David Parker
David Parker is a film producer known for his work on the Australian psychological thriller "In Her Skin."
E893181 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: David Parker | Statement: [In Her Skin, producer, David Parker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Parker
Context triple: [In Her Skin, producer, David Parker]
  • A. David Parker
    David Parker is an Australian politician who notably served as Treasurer of Western Australia.
  • B. David Parker
    David Parker is one of the children of acclaimed American crime novelist Robert B. Parker.
  • C. David Parker
    David Parker is an actor known for his role in the 2001 biographical television film "James Dean."
  • D. Daniel Parker
    Daniel Parker is the son of acclaimed American crime novelist Robert B. Parker.
  • E. Chan Parker
    Chan Parker was the longtime partner and later wife of jazz saxophonist Charlie Parker, known for her close association with the bebop scene and for preserving Parker’s legacy.
  • 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: David Parker
Triple: [In Her Skin, producer, David Parker]
Generated description
David Parker is a film producer known for his work on the Australian psychological thriller "In Her Skin."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: David Parker
Target entity description: David Parker is a film producer known for his work on the Australian psychological thriller "In Her Skin."
  • A. David Parker
    David Parker is one of the children of acclaimed American crime novelist Robert B. Parker.
  • B. David Parker
    David Parker is an actor known for his role in the 2001 biographical television film "James Dean."
  • C. David Parker
    David Parker is an Australian politician who notably served as Treasurer of Western Australia.
  • D. Daniel Parker
    Daniel Parker is the son of acclaimed American crime novelist Robert B. Parker.
  • E. Chan Parker
    Chan Parker was the longtime partner and later wife of jazz saxophonist Charlie Parker, known for her close association with the bebop scene and for preserving Parker’s legacy.
  • 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_69d6aa81a5d08190aa86689061d1ddd2 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d750d0155c81908fb55ba6b45db800 completed April 9, 2026, 7:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2166293808190b7ed1620dfc8a158 completed April 17, 2026, 11:15 a.m.
NEDg Description generation batch_69e21d860d288190855ffbe60df50df9 completed April 17, 2026, 11:46 a.m.
NED2 Entity disambiguation (via description) batch_69e21f09be508190a7c497a7680cb59e completed April 17, 2026, 11:52 a.m.
Created at: April 8, 2026, 9:19 p.m.