Triple
T5116179
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walt Disney World Swan Hotel |
E115339
|
entity |
| Predicate | distanceToEpcotEntrance |
P53174
|
FINISHED |
| Object | walking distance |
—
|
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: walking distance | Statement: [Walt Disney World Swan Hotel, distanceToEpcotEntrance, walking distance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceToEpcotEntrance Context triple: [Walt Disney World Swan Hotel, distanceToEpcotEntrance, walking distance]
-
A.
proximityToLandmark
chosen
Indicates a spatial relationship where one entity is located near or close to a specified landmark.
-
B.
distanceFromDowntown
Indicates the physical distance between a given location and the central downtown area.
-
C.
distanceToGriffith
Indicates the measured or calculated distance between a given entity and Griffith.
-
D.
hasLandmarkAtEntrance
Indicates that a specific landmark is located at or directly adjacent to the entrance of something.
-
E.
distanceFromTerminus
Indicates the measured distance of an entity from a defined endpoint or terminus along a route, path, or sequence.
- 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_69bd4441d1648190a54a533895041987 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd75cfa9f88190aa7dfd264e554899 |
completed | March 20, 2026, 4:29 p.m. |
| PD | Predicate disambiguation | batch_69bd7160d44081908cc64f3c14d28b81 |
completed | March 20, 2026, 4:10 p.m. |
Created at: March 20, 2026, 1:41 p.m.