Triple
T11671197
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cotswold stone |
E277381
|
entity |
| Predicate | hardeningProperty |
P100695
|
FINISHED |
| Object | hardens on exposure to air |
—
|
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: hardens on exposure to air | Statement: [Cotswold stone, hardeningProperty, hardens on exposure to air]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hardeningProperty Context triple: [Cotswold stone, hardeningProperty, hardens on exposure to air]
-
A.
hardness
Indicates the degree to which one entity resists being scratched, indented, or deformed by another.
-
B.
modularProperty
Indicates that one entity possesses a characteristic, behavior, or component that is designed to be separable, interchangeable, or recombinable with others in a modular fashion.
-
C.
isFortifiedWith
Indicates that one entity has been strengthened, enriched, or supplemented by the addition of another entity.
-
D.
coreProtection
Indicates that an entity provides essential safeguarding or defense for another entity’s central or most critical component.
-
E.
protectionType
Indicates the kind or method of protection that is applied to or associated with an entity.
- F. None of above. chosen
Provenance (4 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_69d6aafd0a448190b44da30af8c6c519 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a44264c08190ba1a4a5bcdc9367b |
completed | April 10, 2026, 7:18 a.m. |
| PD | Predicate disambiguation | batch_69d88a77e6e88190b7519100bde76575 |
completed | April 10, 2026, 5:28 a.m. |
| PDg | Predicate description generation | batch_69d8938a1f8c81908ffb049fa5fee5a7 |
completed | April 10, 2026, 6:07 a.m. |
Created at: April 8, 2026, 9:39 p.m.