Triple
T21778592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mosedale Horseshoe |
E537645
|
entity |
| Predicate | hasAlternativeDirection |
P61247
|
FINISHED |
| Object | clockwise |
—
|
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: clockwise | Statement: [Mosedale Horseshoe, hasAlternativeDirection, clockwise]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAlternativeDirection Context triple: [Mosedale Horseshoe, hasAlternativeDirection, clockwise]
-
A.
hasDirectionVariant
chosen
Indicates that one entity is a directional variant or orientation-specific form of another entity.
-
B.
hasDirectionType
Indicates that something possesses or is associated with a specific type or category of direction.
-
C.
hasNumberOfDirections
Indicates that an entity is associated with a specific count of possible directions or orientations.
-
D.
hasAlternativeSurface
Indicates that one entity serves as a different or substitute surface option for another entity.
-
E.
hasAlternateTake
Indicates that one entity is an alternative version or different take of another, typically representing a variant recording, shot, or rendition of the same underlying content.
- 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_69e0c470759c819094a215757113562b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0462b094c81908207073c278a58fe |
completed | April 28, 2026, 5:31 a.m. |
| PD | Predicate disambiguation | batch_69e6be6299988190a34c98fa76d94700 |
completed | April 21, 2026, 12:01 a.m. |
Created at: April 16, 2026, 6:52 p.m.