Triple
T14095645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Achaemenid satrapy of Babylonia |
E339246
|
entity |
| Predicate | recordEvidence |
P3650
|
FINISHED |
| Object | cuneiform economic 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: cuneiform economic tablets | Statement: [Achaemenid satrapy of Babylonia, recordEvidence, cuneiform economic tablets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recordEvidence Context triple: [Achaemenid satrapy of Babylonia, recordEvidence, cuneiform economic tablets]
-
A.
recordDetail
Indicates that one entity stores or documents specific information or attributes about another entity.
-
B.
providesEvidenceFor
chosen
Indicates that one entity serves as support, justification, or proof for the validity or truth of another entity.
-
C.
recordHeldIn
Indicates that a record is stored, maintained, or kept within a particular location, system, or repository.
-
D.
recordKeeper
Indicates a relationship where one entity is responsible for maintaining, managing, or preserving official records or documented information about another entity or activity.
-
E.
recordHeld
Indicates that one entity possesses or maintains a particular record associated with another entity or context.
- 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_69d81c69b5c8819094aa1abf18302908 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5fb7fb3c819083266dbe7e93aaff |
completed | April 14, 2026, 3:39 p.m. |
| PD | Predicate disambiguation | batch_69de05b2f7e481908a9a7d40153234c0 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:22 p.m.