Triple
T7041384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herrero |
E163519
|
entity |
| Predicate | occupationalOrigin |
P8625
|
FINISHED |
| Object | metalworking |
—
|
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: metalworking | Statement: [Herrero, occupationalOrigin, metalworking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: occupationalOrigin Context triple: [Herrero, occupationalOrigin, metalworking]
-
A.
derivesFromOccupation
chosen
Indicates that one entity originates from, is obtained through, or is a result of another entity’s occupation or professional role.
-
B.
isOccupationalFormOf
Indicates that one occupation is a specific form, variant, or specialization of another, more general occupation.
-
C.
sufferedOccupationBy
Indicates that an entity experienced harm, hardship, or adverse conditions as a result of being occupied or controlled by another entity.
-
D.
originallyFromWorkType
Indicates that one entity was derived, adapted, or sourced from an original work of a specified type (e.g., book, film, artwork).
-
E.
earlierOccupation
Indicates that one occupation held by an entity occurred before another occupation in that entity’s work history.
- 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_69c6885e7c1c8190be32a8f79ab4e0cf |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e4a3c36c819080942c59f1830ae8 |
completed | March 27, 2026, 8:12 p.m. |
| PD | Predicate disambiguation | batch_69c6e1bb602081908bfa6186a1f5a4b4 |
completed | March 27, 2026, 7:59 p.m. |
Created at: March 27, 2026, 2:36 p.m.