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.