Triple

T1392615
Position Surface form Disambiguated ID Type / Status
Subject Zadie Smith E29993 entity
Predicate notableWork P4 FINISHED
Object NW
NW is a 2012 novel by British author Zadie Smith that explores the intersecting lives of residents in northwest London, examining themes of class, race, and identity.
 E160178 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: NW | Statement: [Zadie Smith, notableWork, NW]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: NW
Context triple: [Zadie Smith, notableWork, NW]
  • A. NW
    NW is an abbreviation used as a vehicle registration code associated with the German federal state of North Rhine-Westphalia.
  • B. WN
    WN is the IATA airline designator used to identify Southwest Airlines in flight schedules, ticketing, and aviation operations.
  • C. NM
    NM is the standard two-letter U.S. postal abbreviation for the state of New Mexico.
  • D. North
    North is an English surname historically associated with several notable figures in British politics and society.
  • E. North
    North is a 1975 poetry collection by Nobel laureate Seamus Heaney that explores themes of Irish history, violence, and identity through mythic and archaeological imagery.
  • 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: NW
Triple: [Zadie Smith, notableWork, NW]
Generated description
NW is a 2012 novel by British author Zadie Smith that explores the intersecting lives of residents in northwest London, examining themes of class, race, and identity.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: NW
Target entity description: NW is a 2012 novel by British author Zadie Smith that explores the intersecting lives of residents in northwest London, examining themes of class, race, and identity.
  • A. NW
    NW is an abbreviation used as a vehicle registration code associated with the German federal state of North Rhine-Westphalia.
  • B. WN
    WN is the IATA airline designator used to identify Southwest Airlines in flight schedules, ticketing, and aviation operations.
  • C. NM
    NM is the standard two-letter U.S. postal abbreviation for the state of New Mexico.
  • D. North
    North is a 1975 poetry collection by Nobel laureate Seamus Heaney that explores themes of Irish history, violence, and identity through mythic and archaeological imagery.
  • E. North
    North is an English surname historically associated with several notable figures in British politics and society.
  • 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_69a498dc92f8819094a1108f8ac90f43 completed March 1, 2026, 7:51 p.m.
NER Named-entity recognition batch_69a4c360a7f08190ab7e903764b06fdf completed March 1, 2026, 10:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69acde28dd888190baa4a26f96f33e0a completed March 8, 2026, 2:25 a.m.
NEDg Description generation batch_69acded118048190993aed439f1467ea completed March 8, 2026, 2:28 a.m.
NED2 Entity disambiguation (via description) batch_69acdf9b47b08190aaf348a32f6b9d2d completed March 8, 2026, 2:31 a.m.
Created at: March 1, 2026, 7:59 p.m.