Triple

T20152695
Position Surface form Disambiguated ID Type / Status
Subject Split Enz E491473 entity
Predicate hasMember P10 FINISHED
Object Malcolm Green
Malcolm Green is an English-born drummer best known for his work with the New Zealand rock band Split Enz during their late 1970s and early 1980s period.
 E1417370 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: Malcolm Green | Statement: [Split Enz, hasMember, Malcolm Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Malcolm Green
Context triple: [Split Enz, hasMember, Malcolm Green]
  • A. Malcolm Barbour
    Malcolm Barbour is a television producer best known for co-creating the long-running reality TV series "Cops."
  • B. Malcolm Gray
    Malcolm Gray is a South African cricket administrator who served as chairman of the International Cricket Council (ICC).
  • C. Malcolm Simpson
    Malcolm Simpson is a notable individual distinguished enough to be recognized as a prominent bearer of the Simpson surname.
  • D. Malcolm Moore
    Malcolm Moore is a musician known for his performance work associated with the album "All the Lost Souls."
  • E. John McLiam
    John McLiam was an Irish-born American character actor known for his supporting roles in numerous films and television series from the 1950s through the 1980s.
  • 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: Malcolm Green
Triple: [Split Enz, hasMember, Malcolm Green]
Generated description
Malcolm Green is an English-born drummer best known for his work with the New Zealand rock band Split Enz during their late 1970s and early 1980s period.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Malcolm Green
Target entity description: Malcolm Green is an English-born drummer best known for his work with the New Zealand rock band Split Enz during their late 1970s and early 1980s period.
  • A. Malcolm Barbour
    Malcolm Barbour is a television producer best known for co-creating the long-running reality TV series "Cops."
  • B. Malcolm Gray
    Malcolm Gray is a South African cricket administrator who served as chairman of the International Cricket Council (ICC).
  • C. Malcolm Simpson
    Malcolm Simpson is a notable individual distinguished enough to be recognized as a prominent bearer of the Simpson surname.
  • D. Malcolm Moore
    Malcolm Moore is a musician known for his performance work associated with the album "All the Lost Souls."
  • E. John McLiam
    John McLiam was an Irish-born American character actor known for his supporting roles in numerous films and television series from the 1950s through the 1980s.
  • 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_69da6265f8f0819080b29c752a574088 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e667dda9b4819097ff66bb2b50fc21 completed April 20, 2026, 5:52 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0843dc55b081909df320e335066a55 completed May 16, 2026, 10:15 a.m.
NEDg Description generation batch_6a0844a1f6988190bbab91201b2a0d7e completed May 16, 2026, 10:19 a.m.
NED2 Entity disambiguation (via description) batch_6a0845700ec48190bb59acff92e4e616 completed May 16, 2026, 10:22 a.m.
Created at: April 11, 2026, 11:34 p.m.