Triple
T7654053
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khasekhemwy |
E173329
|
entity |
| Predicate | preOldKingdomRole |
P47814
|
FINISHED |
| Object | precursor of Old Kingdom centralization |
—
|
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: precursor of Old Kingdom centralization | Statement: [Khasekhemwy, preOldKingdomRole, precursor of Old Kingdom centralization]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preOldKingdomRole Context triple: [Khasekhemwy, preOldKingdomRole, precursor of Old Kingdom centralization]
-
A.
mainKingCharacter
Indicates that the entity serves as the primary king character or central royal protagonist in a given context.
-
B.
roleInMonarchyPeriod
Indicates that an entity held a specific role or position during a defined period of a monarchy.
-
C.
pre-imperialRole
chosen
Indicates that an entity held a particular role or position during a pre-imperial period, before the establishment of an empire or imperial rule.
-
D.
roleInKingship
Indicates that an entity holds or plays a specific role or position within a system of kingship or royal authority.
-
E.
GameOfThronesRole
Indicates that one entity plays, voices, or otherwise portrays a character in the television series "Game of Thrones" in relation to another entity.
- 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_69c6995473348190a4f41d110d619a18 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7061cbc3c8190a917dd7e71214182 |
completed | March 27, 2026, 10:35 p.m. |
| PD | Predicate disambiguation | batch_69c7015dd8fc8190bc5f52a12bd46209 |
completed | March 27, 2026, 10:14 p.m. |
Created at: March 27, 2026, 3:59 p.m.