Triple
T30138650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sumerian laments for Dumuzi |
E766066
|
entity |
| Predicate | attestedInPeriod |
P41036
|
FINISHED |
| Object | Old Babylonian period |
—
|
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: Old Babylonian period | Statement: [Sumerian laments for Dumuzi, attestedInPeriod, Old Babylonian period]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: attestedInPeriod Context triple: [Sumerian laments for Dumuzi, attestedInPeriod, Old Babylonian period]
-
A.
appearsInTimePeriod
Indicates that an entity is present, active, or occurs within a specified time period.
-
B.
appliedDuringPeriod
Indicates that an action, condition, or status was in effect throughout a specified time period.
-
C.
spokenInPeriod
Indicates that an entity (such as a language, dialect, or way of speaking) was used or spoken during a specific time period.
-
D.
meetsInTimePeriod
Indicates that two entities encounter or come together during a specified time period.
-
E.
locatedInHistoricPeriod
chosen
Indicates that an entity exists, occurs, or is situated within a specific historic period or era.
- 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_69f2247909048190ae86c2160cf8b566 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67e4dfe588190991b0f75728af132 |
completed | May 2, 2026, 10:44 p.m. |
| PD | Predicate disambiguation | batch_69f673c664f08190b4d66cdc305e10db |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:17 p.m.