Triple
T31840562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sumerian royal ideology |
E812789
|
entity |
| Predicate | keyTextualTheme |
P172651
|
FINISHED |
| Object | kingship bestowed by Enlil |
—
|
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: kingship bestowed by Enlil | Statement: [Sumerian royal ideology, keyTextualTheme, kingship bestowed by Enlil]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyTextualTheme Context triple: [Sumerian royal ideology, keyTextualTheme, kingship bestowed by Enlil]
-
A.
keyThemeIn
Indicates that a particular theme is a central or primary thematic focus within a given work, context, or subject.
-
B.
themeKey
Indicates that one entity serves as the primary subject, topic, or thematic focus associated with another entity.
-
C.
keyText
Indicates that a piece of text functions as a key or identifier used to access, reference, or unlock something in a system or context.
-
D.
keyTextByMainProponent
Indicates that the referenced text is a primary or central document authored or put forward by the main proponent of an idea, theory, or position.
-
E.
themeFor
Indicates that something serves as the central subject, topic, or focus for another thing (such as an event, work, or activity).
- F. None of above. chosen
Provenance (4 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_69f348ea7ffc8190a2ab43d80277cf59 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b034bc74819091250f91ba5174c0 |
completed | May 3, 2026, 2:17 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
| PDg | Predicate description generation | batch_69f6af7d92008190aead47eaae8cc091 |
completed | May 3, 2026, 2:14 a.m. |
Created at: April 30, 2026, 11:49 p.m.