Triple
T4244629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Angkor Wat |
E95497
|
entity |
| Predicate | gridReferenceType |
P54915
|
FINISHED |
| Object | temple-mountain layout |
—
|
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: temple-mountain layout | Statement: [Angkor Wat, gridReferenceType, temple-mountain layout]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: gridReferenceType Context triple: [Angkor Wat, gridReferenceType, temple-mountain layout]
-
A.
hasOSGridReference
Indicates that an entity is associated with a specific Ordnance Survey grid reference location.
-
B.
refersToLocation
Indicates that one entity designates, points to, or identifies a specific location associated with it.
-
C.
isReferencePointFor
Indicates that one entity serves as a positional or conceptual basis used to locate, measure, or interpret another entity.
-
D.
referenceSurface
Indicates that one entity serves as the surface or base relative to which another entity is positioned, aligned, or defined.
-
E.
refersToGeographicFeature
Indicates that one entity makes reference to, denotes, or is associated with a specific geographic feature such as a landform, body of water, or other physical location.
- F. None of above. chosen
Provenance (4 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_69b3453d91548190b4d4ef8fe52aa2ac |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34e8c42e88190b309a1ef7f6529ac |
completed | March 12, 2026, 11:38 p.m. |
| PD | Predicate disambiguation | batch_69b347f587148190a1830503459939b6 |
completed | March 12, 2026, 11:10 p.m. |
| PDg | Predicate description generation | batch_69b34e04ef1c81908bb34ae1cbfab1e6 |
completed | March 12, 2026, 11:36 p.m. |
Created at: March 12, 2026, 11:05 p.m.