Triple
T10774879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unas |
E254171
|
entity |
| Predicate | pyramidTextContent |
P43186
|
FINISHED |
| Object | royal funerary spells |
—
|
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: royal funerary spells | Statement: [Unas, pyramidTextContent, royal funerary spells]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pyramidTextContent Context triple: [Unas, pyramidTextContent, royal funerary spells]
-
A.
pyramidTextInscriptions
chosen
Indicates that the subject has text inscriptions located on or within a pyramid.
-
B.
pyramidName
Indicates that a pyramid is associated with a specific name or title.
-
C.
textContent
Indicates that one entity is the textual content or written material contained within another entity.
-
D.
coreText
Indicates that something serves as the main or primary textual content within a larger work or context.
-
E.
pyramidFunction
Indicates a functional or hierarchical relationship where one entity operates at the apex or controlling level over multiple subordinate entities, analogous to a pyramid structure.
- 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_69d6aa609f008190a294200aefcb7bd5 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7329be784819083b7ec4d85c20acf |
completed | April 9, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69d6f31455648190b5c24690487b1b54 |
completed | April 9, 2026, 12:30 a.m. |
Created at: April 8, 2026, 9:16 p.m.