Triple
T26653461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Causeway of Khafre |
E666430
|
entity |
| Predicate | terminusAtPlateau |
P388
|
FINISHED |
| Object | mortuary temple of Khafre |
—
|
NE NERFINISHED |
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: mortuary temple of Khafre | Statement: [Causeway of Khafre, terminusAtPlateau, mortuary temple of Khafre]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: terminusAtPlateau Context triple: [Causeway of Khafre, terminusAtPlateau, mortuary temple of Khafre]
-
A.
terminus
chosen
Indicates that one entity serves as the final endpoint or stopping place for another entity’s movement, route, or process.
-
B.
hasPlateaus
Indicates that something possesses or contains one or more plateau-like flat elevated areas.
-
C.
terminusUpper
Indicates that one entity serves as the upper or final endpoint (terminus) of another entity, such as a route, segment, or ordered structure.
-
D.
locatedOnPlateauBetween
Indicates that one entity is situated on a plateau that lies between two other referenced geographic or spatial entities.
-
E.
hasPlateauSize
Indicates that an entity possesses or is characterized by a specific plateau size, typically referring to the extent or magnitude of a flat or stable region.
- 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_69ee9cf8c7188190b9b00270a8a89164 |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f650c70d7c819093d9a0f005f7c8d5 |
completed | May 2, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69f64cab1f648190a2a9460690d18a37 |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 27, 2026, 2:34 a.m.