Triple
T29132942
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chipping Norton textile industry |
E738427
|
entity |
| Predicate | usedFacilityType |
P2836
|
FINISHED |
| Object | water-powered mills |
—
|
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: water-powered mills | Statement: [Chipping Norton textile industry, usedFacilityType, water-powered mills]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedFacilityType Context triple: [Chipping Norton textile industry, usedFacilityType, water-powered mills]
-
A.
usedAtFacilityType
Indicates that something is utilized or applied within a facility of a specified type.
-
B.
usesFacilityFor
Indicates that an entity makes use of a particular facility to carry out a specific purpose, activity, or function.
-
C.
usedFacilityName
Indicates that an entity made use of a facility identified by a particular name.
-
D.
designedFacilityType
Indicates the type or category of facility that something (such as a plan, system, or component) is specifically designed for.
-
E.
hasFacilityType
chosen
Indicates that an entity possesses or is associated with a specific type or category of facility.
- 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_69f07cb3adb48190a9e0e169cd026634 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f7308a096081909d66a56f3c926806 |
completed | May 3, 2026, 11:24 a.m. |
| PD | Predicate disambiguation | batch_69f72a00c5f081908b6539d15baf4e12 |
completed | May 3, 2026, 10:57 a.m. |
Created at: April 28, 2026, 11:32 a.m.