Triple
T30404133
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Temple of Ninurta |
E773430
|
entity |
| Predicate | hasDirectionFromMainPalace |
P194423
|
FINISHED |
| Object | within citadel of Nimrud |
—
|
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: within citadel of Nimrud | Statement: [Temple of Ninurta, hasDirectionFromMainPalace, within citadel of Nimrud]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDirectionFromMainPalace Context triple: [Temple of Ninurta, hasDirectionFromMainPalace, within citadel of Nimrud]
-
A.
hasAncestralPalace
Indicates that an entity possesses or is associated with a palace inherited from its ancestors or historically belonging to its lineage.
-
B.
palaceLocatedIn
Indicates that a palace is situated within or belongs to a specific geographic or administrative location.
-
C.
otherOfficialPalace
Indicates that one entity serves as another entity’s alternative or additional official palace.
-
D.
hasImperialPalace
Indicates that an entity possesses or is the location of an official imperial palace.
-
E.
hasNumberOfPalaces
Indicates the specific count of palaces associated with an entity.
- 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_69f2248facd48190b183c3f3ca6daef7 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fd6f9d600c8190acf495b7fc632e4b |
completed | May 8, 2026, 5:07 a.m. |
| PD | Predicate disambiguation | batch_69fd6e98a2948190a9f78c415ad23b8c |
completed | May 8, 2026, 5:03 a.m. |
| PDg | Predicate description generation | batch_69fd6f9a8bd881909983fe8f4cd0ba98 |
completed | May 8, 2026, 5:07 a.m. |
Created at: April 29, 2026, 8:03 p.m.