Triple
T21179562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uluwatu Temple |
E521907
|
entity |
| Predicate | guardianDirection |
P101901
|
FINISHED |
| Object | southwest |
—
|
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: southwest | Statement: [Uluwatu Temple, guardianDirection, southwest]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: guardianDirection Context triple: [Uluwatu Temple, guardianDirection, southwest]
-
A.
guardian
Indicates a protective or custodial relationship in which one entity is responsible for the care, safety, or oversight of another.
-
B.
directionGuarded
chosen
Indicates that one entity protects, blocks, or oversees another entity specifically from a given direction or along a particular directional axis.
-
C.
guardianShrineOf
Indicates a relationship where one entity serves as a protective or custodial shrine dedicated to another entity.
-
D.
typicalGuard
Indicates that an entity commonly or characteristically serves in a guarding or protective role relative to another entity or context.
-
E.
guard
Indicates that one entity protects, watches over, or defends another entity or resource from harm, intrusion, or unauthorized access.
- 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_69e0b50ef1d48190b063aa342667df22 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7301c842c8190b969a8b3f194003a |
completed | April 21, 2026, 8:06 a.m. |
| PD | Predicate disambiguation | batch_69e5f6027c248190a170a36612bd337e |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 3:01 p.m.