Triple
T37334576
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ruriko-ji Temple |
E926851
|
entity |
| Predicate | hasAltitudeType |
P50137
|
FINISHED |
| Object | lowland temple setting |
—
|
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: lowland temple setting | Statement: [Ruriko-ji Temple, hasAltitudeType, lowland temple setting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAltitudeType Context triple: [Ruriko-ji Temple, hasAltitudeType, lowland temple setting]
-
A.
hasAltitudeFeature
chosen
Indicates that an entity possesses a characteristic or attribute related to its elevation or vertical position above a reference level.
-
B.
hasAltitudeStation
Indicates that something is associated with or located at a station characterized by a specific altitude.
-
C.
hasAltitudeDifference
Indicates that there is a specific vertical height difference between two entities or locations.
-
D.
supportsAltitudeMode
Indicates that one entity is capable of operating in or is compatible with a specified altitude control or altitude-related operating mode of another entity.
-
E.
unitOfAltitude
Indicates the measurement unit used to express an altitude value in a given context.
- 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_69f76eb4e8a881908bd40da28f36fc7e |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fe6e492bf8819080b25221d13445ea |
completed | May 8, 2026, 11:14 p.m. |
| PD | Predicate disambiguation | batch_69fe6dd33a6881908fe9bbbc184cab51 |
completed | May 8, 2026, 11:12 p.m. |
Created at: May 3, 2026, 4:16 p.m.