Triple
T18694153
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ziusudra |
E457071
|
entity |
| Predicate | sourceMaterialState |
P8734
|
FINISHED |
| Object | fragmentary cuneiform tablets |
—
|
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: fragmentary cuneiform tablets | Statement: [Ziusudra, sourceMaterialState, fragmentary cuneiform tablets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sourceMaterialState Context triple: [Ziusudra, sourceMaterialState, fragmentary cuneiform tablets]
-
A.
sourceMaterialType
Indicates the type or category of material from which something originates or is derived.
-
B.
sourceMaterialSetting
Indicates that one entity serves as the contextual or environmental setting in which the source material of another entity is situated or occurs.
-
C.
sourceState
chosen
Indicates the original or starting state from which a transition, change, or process begins.
-
D.
materialSource
Indicates that one entity serves as the origin or provider of the material or substance used by another entity.
-
E.
hasSourceMaterial
Indicates that something is derived from, based on, or created using a particular source material.
- 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_69d8d391eb488190ac2e9abf5bf255e4 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e562e581f48190997d279296a31e7f |
completed | April 19, 2026, 11:19 p.m. |
| PD | Predicate disambiguation | batch_69e478de85088190ba5f005f1d39f587 |
completed | April 19, 2026, 6:40 a.m. |
Created at: April 10, 2026, 11:49 a.m.