Triple
T28053171
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pirate Galleon (Disneyland Paris) |
E708881
|
entity |
| Predicate | walkthrough |
P105220
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Pirate Galleon (Disneyland Paris), walkthrough, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: walkthrough Context triple: [Pirate Galleon (Disneyland Paris), walkthrough, yes]
-
A.
walkThrough
chosen
Indicates moving through or along the interior or extent of something, typically traversing a space or environment from one side or point to another.
-
B.
hasWalkthroughArea
Indicates that one entity includes or provides a designated area intended for walking through or passing along.
-
C.
walks
Indicates that an entity moves on foot from one place to another, typically at a regular, moderate pace.
-
D.
tourOf
Indicates that one entity serves as a guided or organized visit through another entity, typically for exploration, education, or sightseeing.
-
E.
walkingTrack
Indicates a designated path or route intended for people to walk along for exercise, leisure, or transit.
- 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_69ef9b6df9f48190bbb971d02cbe1b65 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f63fdad1d88190b22cd7ace33556fd |
completed | May 2, 2026, 6:18 p.m. |
| PD | Predicate disambiguation | batch_69f637120c008190b2b5adf46f022e48 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 8:34 p.m.