Triple
T11794638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Desert Temple |
E280472
|
entity |
| Predicate | canGenerateWith |
P23101
|
FINISHED |
| Object | Partially buried structure |
—
|
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: Partially buried structure | Statement: [Desert Temple, canGenerateWith, Partially buried structure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canGenerateWith Context triple: [Desert Temple, canGenerateWith, Partially buried structure]
-
A.
canBeConstructedWith
chosen
Indicates that one entity can be formed, built, or assembled using another entity as material, components, or means.
-
B.
hasGeneratingFunction
Indicates that one entity serves as the generating function associated with, or defining, another entity.
-
C.
canUse
Indicates that one entity has the ability, permission, or suitability to make use of another entity or resource.
-
D.
canBeImplementedWith
Indicates that one entity is capable of being realized, executed, or fulfilled through the use or application of another entity.
-
E.
canMake
Indicates that one entity has the ability or capacity to create, produce, or assemble another entity.
- 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_69d6ab258b808190b1735835c841e3a4 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a5a082d08190a42541396a06ed98 |
completed | April 10, 2026, 7:24 a.m. |
| PD | Predicate disambiguation | batch_69d8a2491f048190853239bc05090bf4 |
completed | April 10, 2026, 7:10 a.m. |
Created at: April 8, 2026, 9:42 p.m.