Triple
T904000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abu Simbel temples |
E19505
|
entity |
| Predicate | originallyCarvedInto |
P11047
|
FINISHED |
| Object | sandstone cliff |
—
|
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: sandstone cliff | Statement: [Abu Simbel temples, originallyCarvedInto, sandstone cliff]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originallyCarvedInto Context triple: [Abu Simbel temples, originallyCarvedInto, sandstone cliff]
-
A.
carvedBy
Indicates that one entity has been shaped, cut, or sculpted from a material by another entity through a carving process.
-
B.
originallyIn
Indicates that something first appeared, was created, or was initially located within a particular context, source, or place.
-
C.
originallyBuiltBy
Indicates that something was first constructed or created by a particular agent, organization, or entity.
-
D.
isInscribedOn
Indicates that text, symbols, or markings are written, carved, or otherwise permanently placed onto the surface of an object.
-
E.
builtFrom
chosen
Indicates that one entity is constructed, composed, or formed using another entity as its material, component, or source.
- 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_69a4939e889c8190ac148b3ac1a7f90b |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ad58334881908df191140b786780 |
completed | March 1, 2026, 9:19 p.m. |
| PD | Predicate disambiguation | batch_69a4aa98caec8190bbcc38320090f058 |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:39 p.m.