Triple
T273732
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miller |
E5201
|
entity |
| Predicate | refersToOccupation |
P2374
|
FINISHED |
| Object | person who worked in a grain mill |
—
|
LITERAL FINISHED |
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: person who worked in a grain mill | Statement: [Miller, refersToOccupation, person who worked in a grain mill]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refersToOccupation Context triple: [Miller, refersToOccupation, person who worked in a grain mill]
-
A.
subjectOccupation
chosen
Indicates that the subject holds or performs a particular job, profession, or role as their occupation.
-
B.
refersToRole
Indicates that one entity designates, mentions, or points to another entity specifically in its capacity as a role or position.
-
C.
sponsorOccupation
Indicates that one entity serves as the occupation or professional role of a sponsor associated with another entity.
-
D.
portraysProfession
Indicates that one entity depicts or represents another entity in a specific profession or occupational role.
-
E.
describesCareerOf
Indicates that one entity provides a description or characterization of the professional career of another entity.
- F. None of above.
Provenance (3 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_69a257e6c8788190987dfe705ca2912a |
completed | Feb. 28, 2026, 2:50 a.m. |
| NER | Named-entity recognition | batch_69a25dd0a99c819089968a5400c58c5f |
completed | Feb. 28, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69a25b7345c4819086c21710864a1b42 |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 2:59 a.m.