Triple
T34254949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BoardWalk Ice Cream |
E878849
|
entity |
| Predicate | walkableFrom |
P90518
|
FINISHED |
| Object | EPCOT International Gateway entrance |
—
|
NE NERFINISHED |
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: EPCOT International Gateway entrance | Statement: [BoardWalk Ice Cream, walkableFrom, EPCOT International Gateway entrance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: walkableFrom Context triple: [BoardWalk Ice Cream, walkableFrom, EPCOT International Gateway entrance]
-
A.
isWalkable
Indicates that an entity can be traversed on foot, typically without obstruction or restriction.
-
B.
hasNearbyWalkingRoutes
Indicates that there are walkable paths or routes located close to the referenced entity.
-
C.
hasWalkingRouteConnection
chosen
Indicates that there is a walkable path or route directly connecting two locations.
-
D.
hasWalkingRouteType
Indicates that an entity is associated with a specific type or category of walking route (e.g., trail, path, or walking itinerary).
-
E.
hasWalkingPathAround
Indicates that one entity has a walking path that encircles or runs around another entity.
- 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_69f349b421cc8190b4b4655e1d612548 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71362f1448190985a80ce7af475cb |
completed | May 3, 2026, 9:20 a.m. |
| PD | Predicate disambiguation | batch_69f7127884388190884f23d181a65d19 |
completed | May 3, 2026, 9:16 a.m. |
Created at: May 1, 2026, 1:56 a.m.