Triple
T1085358
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Red Crown |
E24037
|
entity |
| Predicate | writtenInHieroglyphsAs |
P22774
|
FINISHED |
| Object | deshret sign |
—
|
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: deshret sign | Statement: [Red Crown, writtenInHieroglyphsAs, deshret sign]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: writtenInHieroglyphsAs Context triple: [Red Crown, writtenInHieroglyphsAs, deshret sign]
-
A.
ancientEgyptianName
Indicates that one entity is the ancient Egyptian name or designation historically used for the other entity.
-
B.
scriptOfInscription
chosen
Indicates the writing system or script in which a given inscription is written.
-
C.
materialTypicallyInscribedOn
Indicates the material that is most commonly used as the surface or medium on which something is inscribed.
-
D.
inscriptionTranslation
Indicates that a provided text expresses the translated content of a specific inscription.
-
E.
majorPharaoh
Indicates that the subject is recognized as a principal or highly significant pharaoh in relation to the object (such as a period, dynasty, or context).
- 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_69a49404428c819092dcc9632f5f7b8b |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b961d0cc8190858296b44fab2f32 |
completed | March 1, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69a4b7407914819092ed933a7316b450 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:42 p.m.