Triple
T22851951
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shisa figurines |
E566375
|
entity |
| Predicate | typicallyPlacedAt |
P91034
|
FINISHED |
| Object | rooftops |
—
|
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: rooftops | Statement: [Shisa figurines, typicallyPlacedAt, rooftops]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicallyPlacedAt Context triple: [Shisa figurines, typicallyPlacedAt, rooftops]
-
A.
oftenLocatedAt
chosen
Indicates that an entity is frequently or commonly found at, or associated with being in, a particular location.
-
B.
oftenLocatedAs
Indicates that one entity is frequently found or situated in the same place as another entity.
-
C.
designedToPlace
Indicates that something is intentionally created or configured for the purpose of positioning or setting another entity in a specific place or arrangement.
-
D.
locatedIn
Indicates that one entity exists or is situated within the spatial, administrative, or conceptual boundaries of another entity.
-
E.
targetedPlace
Indicates that an entity intentionally directed an action, operation, or influence toward a specific place or location.
- 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_69e2458750b481908a8e4cf4609cc6cf |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17eb9a5b8819091cbb4ac42fbf778 |
completed | April 29, 2026, 3:44 a.m. |
| PD | Predicate disambiguation | batch_69eed2d507c08190895ed971af0fc755 |
completed | April 27, 2026, 3:07 a.m. |
Created at: April 17, 2026, 3:36 p.m.