Triple
T22240879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prichard |
E549717
|
entity |
| Predicate | isNamedEntityType |
P12498
|
FINISHED |
| Object | geographical location |
—
|
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: geographical location | Statement: [Prichard, isNamedEntityType, geographical location]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isNamedEntityType Context triple: [Prichard, isNamedEntityType, geographical location]
-
A.
isNamedEntity
chosen
Indicates that the subject is recognized as a named entity, such as a specific person, organization, location, or other proper noun.
-
B.
isNamedUnit
Indicates that an entity is a unit of measurement that has an explicit, conventional name rather than being expressed purely in derived or composite form.
-
C.
isEntityOf
Indicates that one entity serves as the defining instance, member, or realization of another, more general entity or concept.
-
D.
isNamedInfrastructure
Indicates that an entity is an infrastructure object that has an assigned specific name or designation.
-
E.
identifiesEntityType
Indicates that one entity specifies or determines the type or category to which another entity belongs.
- 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_69e11e4102b881909cf47d3768e25c19 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f132140ed481909ab0d4022756a4ba |
completed | April 28, 2026, 10:17 p.m. |
| PD | Predicate disambiguation | batch_69e72fe1e0cc8190bd13cff2a0846225 |
completed | April 21, 2026, 8:05 a.m. |
Created at: April 16, 2026, 8:38 p.m.