Triple
T10087200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nuffar |
E215250
|
entity |
| Predicate | hasRoleInAncientMesopotamia |
P91989
|
FINISHED |
| Object | religious capital of Sumer |
—
|
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: religious capital of Sumer | Statement: [Nuffar, hasRoleInAncientMesopotamia, religious capital of Sumer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRoleInAncientMesopotamia Context triple: [Nuffar, hasRoleInAncientMesopotamia, religious capital of Sumer]
-
A.
associatedWithAncientEmpire
Indicates that one entity has a historical, cultural, political, or geographic connection or affiliation with an ancient empire.
-
B.
hasAncientCityState
Indicates that one entity possesses, contains, or is associated with an ancient city-state as part of its historical or geographical context.
-
C.
nameInSumerian
Indicates that an entity is known or referred to by a specific name in the Sumerian language.
-
D.
ancientStates
Indicates that the related entity functioned as a state or political entity in ancient times.
-
E.
isAncient
Indicates that the entity existed or originated in a very distant past, typically far earlier than the commonly referenced historical period.
- 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_69ca83a1eed081908b2e9580f2ebeea7 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdd04745b48190a77c422eb76b6660 |
completed | April 2, 2026, 2:11 a.m. |
| PD | Predicate disambiguation | batch_69cd4b97870481908f7a89df10d58a9e |
completed | April 1, 2026, 4:45 p.m. |
| PDg | Predicate description generation | batch_69cd4f8d9b888190b8067bd916dae773 |
completed | April 1, 2026, 5:02 p.m. |
Created at: March 30, 2026, 9:01 p.m.