Triple
T276485
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fields Corner |
E5259
|
entity |
| Predicate | hasAccessibilityFeatures |
P182
|
FINISHED |
| Object | elevators |
—
|
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: elevators | Statement: [Fields Corner, hasAccessibilityFeatures, elevators]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAccessibilityFeatures Context triple: [Fields Corner, hasAccessibilityFeatures, elevators]
-
A.
hasFeature
chosen
Indicates that an entity possesses, exhibits, or includes a particular characteristic, attribute, or component.
-
B.
supportsFeature
Indicates that one entity provides, enables, or is compatible with a particular feature or capability of another.
-
C.
hasAccessMode
Indicates the type or method of access that one entity is permitted to use with respect to another entity or resource.
-
D.
hasCharacteristic
Indicates that an entity possesses, exhibits, or is defined by a particular attribute, feature, or quality.
-
E.
accessible
Indicates that one entity can be reached, entered, used, or understood by another entity, often without undue difficulty or barriers.
- 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_69a257e6c8788190987dfe705ca2912a |
completed | Feb. 28, 2026, 2:50 a.m. |
| NER | Named-entity recognition | batch_69a25dec53ac8190912f3d79576131fa |
completed | Feb. 28, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69a25b7480e881909399beccfc7ffb81 |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 2:59 a.m.