Triple
T30164558
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Temple of Ningirsu at Girsu |
E766760
|
entity |
| Predicate | reconstructionDescribedIn |
P156997
|
FINISHED |
| Object | Gudea cylinders |
—
|
NE NERFINISHED |
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: Gudea cylinders | Statement: [Temple of Ningirsu at Girsu, reconstructionDescribedIn, Gudea cylinders]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reconstructionDescribedIn Context triple: [Temple of Ningirsu at Girsu, reconstructionDescribedIn, Gudea cylinders]
-
A.
reconstructionDetails
chosen
Indicates that there is information specifying how something was rebuilt, restored, or reassembled after damage, loss, or alteration.
-
B.
reconstructedIn
Indicates that something has been rebuilt, restored, or re-created within a particular context, location, or medium.
-
C.
reconstructionUsedIn
Indicates that a particular reconstruction (e.g., a restored version or inferred structure) is employed or applied within a given context, process, or work.
-
D.
reconstructionFor
Indicates that one entity serves as a reconstruction, restoration, or rebuilt version of another entity.
-
E.
reconstructs
Indicates performing an action to rebuild, restore, or reassemble something from its parts, damage, or prior state.
- 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_69f2247a968881909d79c18f2bfcb275 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67f06825c819088cfc20337be8319 |
completed | May 2, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69f673c7a4588190837854f3ef61e6bf |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:22 p.m.