Triple
T5338668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ploutonion |
E123887
|
entity |
| Predicate | spatialAssociation |
P17188
|
FINISHED |
| Object | caves |
—
|
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: caves | Statement: [Ploutonion, spatialAssociation, caves]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spatialAssociation Context triple: [Ploutonion, spatialAssociation, caves]
-
A.
spatialRelation
chosen
Indicates a spatial relationship between entities, specifying how one is positioned or located relative to another in space.
-
B.
spatialProperty
Indicates a relationship where one entity has a specific spatial characteristic, such as position, size, orientation, or geometric configuration in space, relative to a reference frame or other entities.
-
C.
arealRelation
Indicates a spatial relationship between areas, such as overlap, containment, adjacency, or relative positioning between two regions.
-
D.
datumRelation
Indicates a relationship where one piece of data is connected to, derived from, or otherwise associated with another piece of data.
-
E.
collocatedWith
Indicates that two entities are located in the same place or spatial context at the same time.
- 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_69bd464b07f8819095aa76577c9829e4 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd85e86edc81908d87933db6489f91 |
completed | March 20, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69bd845a62b081909782863865b257a9 |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2 p.m.