Triple
T20531310
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Autograph Collection Hotels |
E504072
|
entity |
| Predicate | amenityStandard |
P5622
|
FINISHED |
| Object | on-site dining |
—
|
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: on-site dining | Statement: [Autograph Collection Hotels, amenityStandard, on-site dining]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: amenityStandard Context triple: [Autograph Collection Hotels, amenityStandard, on-site dining]
-
A.
amenity
chosen
Indicates that one entity provides a useful facility, service, or feature that enhances the convenience or comfort of another entity.
-
B.
amenityLevel
Indicates the degree or quality of facilities, services, or conveniences provided in relation to something.
-
C.
typicalAmenity
Indicates that something is a common or characteristic amenity typically associated with a given entity or context.
-
D.
amenityFocus
Indicates a relationship where an amenity is specifically oriented toward, designed for, or primarily serving a particular focus or target (such as a user group, activity, or purpose).
-
E.
hasAmenityAccessTo
Indicates that an entity has the right or ability to use or benefit from a specified amenity or 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_69e0b4b3a6e08190ae663701f50fab8e |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a06b923c81908ba24be6645a7c61 |
completed | April 20, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69e59fdb7ad88190924176c32a195db3 |
completed | April 20, 2026, 3:39 a.m. |
Created at: April 16, 2026, 11:37 a.m.