Triple

T16475635
Position Surface form Disambiguated ID Type / Status
Subject B. Traven E400179 entity
Predicate hasPseudonym P3799 FINISHED
Object Hal Croves
Hal Croves is a pseudonym used by the mysterious 20th-century novelist B. Traven, whose true identity has long been the subject of speculation.
E1217968 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: Hal Croves | Statement: [B. Traven, hasPseudonym, Hal Croves]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hal Croves
Context triple: [B. Traven, hasPseudonym, Hal Croves]
  • A. Eric Crozier
    Eric Crozier was a British theatrical director, producer, and writer best known for his close collaboration with composer Benjamin Britten on several operas.
  • B. Ian Crocker
    Ian Crocker is an American former competitive swimmer and multiple Olympic gold medalist known for his world records in butterfly events.
  • C. Ian Crafford
    Ian Crafford is a film editor best known for his work on the family fantasy movie "The Indian in the Cupboard."
  • D. Ian Crafford
    Ian Crafford is a film editor best known for his work on the James Bond movie "Never Say Never Again."
  • E. Tim Holbrook
    Tim Holbrook is an American legal scholar known for his work in intellectual property and patent law.
  • 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: Hal Croves
Triple: [B. Traven, hasPseudonym, Hal Croves]
Generated description
Hal Croves is a pseudonym used by the mysterious 20th-century novelist B. Traven, whose true identity has long been the subject of speculation.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hal Croves
Target entity description: Hal Croves is a pseudonym used by the mysterious 20th-century novelist B. Traven, whose true identity has long been the subject of speculation.
  • A. Eric Crozier
    Eric Crozier was a British theatrical director, producer, and writer best known for his close collaboration with composer Benjamin Britten on several operas.
  • B. Ian Crocker
    Ian Crocker is an American former competitive swimmer and multiple Olympic gold medalist known for his world records in butterfly events.
  • C. Ian Crafford
    Ian Crafford is a film editor best known for his work on the James Bond movie "Never Say Never Again."
  • D. Ian Crafford
    Ian Crafford is a film editor best known for his work on the family fantasy movie "The Indian in the Cupboard."
  • E. Tim Holbrook
    Tim Holbrook is an American legal scholar known for his work in intellectual property and patent law.
  • 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_69d883813098819084f5409539723b59 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32dd43cf88190881a5cbc80da1490 completed April 18, 2026, 7:08 a.m.
NED1 Entity disambiguation (via context triple) batch_6a006078da4c8190ba510d92b503e993 completed May 10, 2026, 10:39 a.m.
NEDg Description generation batch_6a0061a6e1e88190a5efe0430db0bd9b completed May 10, 2026, 10:44 a.m.
NED2 Entity disambiguation (via description) batch_6a00627908988190803707069872e4c5 completed May 10, 2026, 10:48 a.m.
Created at: April 10, 2026, 5:13 a.m.