Triple

T33727560
Position Surface form Disambiguated ID Type / Status
Subject Milton the Magician E864184 entity
Predicate employsEarlyInCareerOf P182789 FINISHED
Object Robert Angier NE NERFINISHED

How this triple was built (2 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: Robert Angier | Statement: [Milton the Magician, employsEarlyInCareerOf, Robert Angier]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: employsEarlyInCareerOf
Context triple: [Milton the Magician, employsEarlyInCareerOf, Robert Angier]
  • A. earlyCareerAt
    Indicates that an entity spent the early part of its career working at or being affiliated with another entity.
  • B. earlyCareerActivity
    Indicates activities, roles, or engagements undertaken by an entity during the early stage of its career or professional development.
  • C. studCareerBegan
    Indicates that a student's professional or academic career started at a specified time or institution.
  • D. earliestOccupation
    Indicates that the associated occupation is the first or earliest known job or professional role held by the person in question.
  • E. earlyOccupation
    Indicates that an entity held a particular occupation or job during an early stage of its life or career.
  • F. None of above. chosen

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_69f3498a64cc8190b4b414c67b280d93 completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69f7908ec35881909a42f954fb9fa16e completed May 3, 2026, 6:14 p.m.
PD Predicate disambiguation batch_69f78e2ac3fc819081a45c6841375c8d completed May 3, 2026, 6:04 p.m.
PDg Predicate description generation batch_69f78fd3fd888190b7db0b563f298585 completed May 3, 2026, 6:11 p.m.
Created at: May 1, 2026, 1:44 a.m.