Triple
T6216170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Potter |
E138992
|
entity |
| Predicate | relatedNameType |
P3889
|
FINISHED |
| Object | derived from an occupational term for a maker of pottery |
—
|
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: derived from an occupational term for a maker of pottery | Statement: [Potter, relatedNameType, derived from an occupational term for a maker of pottery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedNameType Context triple: [Potter, relatedNameType, derived from an occupational term for a maker of pottery]
-
A.
relatedType
Indicates that one entity is connected to another through a specified type or category of relationship.
-
B.
relationshipType
Indicates the specific kind of relationship that exists between two or more entities.
-
C.
associatedName
Indicates that one entity has an alternative or related name that is linked or connected to another entity.
-
D.
termRelationTo
Indicates a general relational association between one term and another, without specifying the exact nature of that relationship.
-
E.
isRelatedName
chosen
Indicates that one name is connected to another through a variant, derivative, or otherwise non-identical but related naming relationship.
- 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_69c008aecb0c81909984b48f733ce8ae |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c062a1eb3881908c7f735cf9c429ce |
completed | March 22, 2026, 9:44 p.m. |
| PD | Predicate disambiguation | batch_69c055fdea3c81908f5d910f0d36234a |
completed | March 22, 2026, 8:50 p.m. |
Created at: March 22, 2026, 4:21 p.m.