Triple
T30179692
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sumerian calendar |
E767166
|
entity |
| Predicate | dayCountPerMonthBasis |
P112806
|
FINISHED |
| Object | synodic lunar cycle |
—
|
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: synodic lunar cycle | Statement: [Sumerian calendar, dayCountPerMonthBasis, synodic lunar cycle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dayCountPerMonthBasis Context triple: [Sumerian calendar, dayCountPerMonthBasis, synodic lunar cycle]
-
A.
hasDayCount
Indicates that an entity is associated with a specific number of days, expressing the duration or count of days related to it.
-
B.
dayCountDependsOn
Indicates that the number of days for one element is determined or constrained by another element.
-
C.
hasNumberOfDaysIn13thMonth
Indicates the specific count of days that occur in the thirteenth month of a given calendar or time system.
-
D.
hasMonthCount
Indicates a relationship where an entity is associated with a specific number of months.
-
E.
monthLengthBasedOn
chosen
Indicates that the length or duration of a month is determined according to a specified basis, rule, or reference system.
- 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_69f2247ba20c81909d34f2bfed706e1e |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67f40e2808190b08d8870702a3f5c |
completed | May 2, 2026, 10:48 p.m. |
| PD | Predicate disambiguation | batch_69f673c7a4588190837854f3ef61e6bf |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:26 p.m.