Triple

T5929593
Position Surface form Disambiguated ID Type / Status
Subject Joe Keller E131901 entity
Predicate formerEmployee P1910 FINISHED
Object Steve Deever E569431 NE FINISHED

How this triple was built (3 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: Steve Deever | Statement: [Joe Keller, formerEmployee, Steve Deever]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steve Deever
Context triple: [Joe Keller, formerEmployee, Steve Deever]
  • A. Steve Deever chosen
    Steve Deever is a character in Arthur Miller’s play "All My Sons," a former business partner scapegoated and imprisoned for a wartime manufacturing crime.
  • B. Steven Dillingham
    Steven Dillingham is an American government official who served as Director of the U.S. Census Bureau during the 2020 United States census.
  • C. Phil Wenneck
    Phil Wenneck is a charismatic, fast-talking schoolteacher and member of the "Wolfpack" whose misadventures drive much of the comedy in The Hangover film series.
  • D. David Scearce
    David Scearce is a Canadian screenwriter best known for adapting Christopher Isherwood’s novel into the acclaimed film "A Single Man."
  • E. John Eisendrath
    John Eisendrath is a television writer and producer best known for his work on series such as "The Blacklist" and "Alias."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: formerEmployee
Context triple: [Joe Keller, formerEmployee, Steve Deever]
  • A. formerEmployer chosen
    Indicates that one entity previously employed the other but no longer does so.
  • B. formerUser
    Indicates that an entity was previously a user of another entity or system but is no longer one.
  • C. employer
    Indicates a relationship where one entity hires, pays, and oversees the work of another entity.
  • D. formerPartner
    Indicates that one entity was previously in a romantic or partnership relationship with another entity, but that relationship has since ended.
  • E. formerMedium
    Indicates that an entity previously used a particular medium or channel but no longer does so.
  • F. None of above.

Provenance (4 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_69c0085b75e88190a632f9691f9da48b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c03c9239e08190bff7ef2bd6d21ae0 completed March 22, 2026, 7:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1355102c88190b139ba052e12a875 completed March 23, 2026, 12:42 p.m.
PD Predicate disambiguation batch_69c033541d108190a34d1fde2fe9dacb completed March 22, 2026, 6:22 p.m.
Created at: March 22, 2026, 4 p.m.