Triple
T9640624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mycerinus |
E233054
|
entity |
| Predicate | pyramidRelativeSizeAtGiza |
P31106
|
FINISHED |
| Object | smallest of the three main pyramids |
—
|
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: smallest of the three main pyramids | Statement: [Mycerinus, pyramidRelativeSizeAtGiza, smallest of the three main pyramids]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pyramidRelativeSizeAtGiza Context triple: [Mycerinus, pyramidRelativeSizeAtGiza, smallest of the three main pyramids]
-
A.
pyramidRankAtGiza
chosen
Indicates the relative ranking or ordered position of a pyramid within the set of pyramids located at Giza.
-
B.
distanceFromGizaPlateau
Indicates the measured spatial distance between a given location and the Giza Plateau.
-
C.
pyramidDesignation
Indicates that one entity is formally designated or classified as a pyramid in relation to another entity or context.
-
D.
pyramidionRestored
Indicates that a pyramidion (the capstone of a pyramid or obelisk) has been returned to its original or intended condition after damage, loss, or alteration.
-
E.
rotationPeriodOfPyramid
Indicates the duration of time it takes for a specified pyramid to complete one full rotation around its axis.
- 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_69ca848a5a908190aad251f4137b0c3a |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9b552a1c81909a1fab347110eeb1 |
completed | April 1, 2026, 10:25 p.m. |
| PD | Predicate disambiguation | batch_69ccd5b0263081908cf6df3eb07d71b0 |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:12 p.m.