Triple
T113506
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hebrew calendar |
E2294
|
entity |
| Predicate | hasAverageMonthLength |
P6443
|
FINISHED |
| Object | about 29.5 days |
—
|
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: about 29.5 days | Statement: [Hebrew calendar, hasAverageMonthLength, about 29.5 days]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAverageMonthLength Context triple: [Hebrew calendar, hasAverageMonthLength, about 29.5 days]
-
A.
hasSolarDayLength
Indicates that an entity is associated with a specific duration for one complete solar day (the time between successive noons).
-
B.
hasMeanRadius
Indicates that an entity possesses a specified average radius measurement, typically representing the mean distance from its center to its surface.
-
C.
hasRotationPeriod
Indicates that one entity has a specified duration for completing a full rotation around its own axis.
-
D.
monthObserved
Indicates the month during which an event, observation, or measurement took place.
-
E.
hasOrbitalPeriod
Indicates that one entity completes a full orbit around another entity within a specified duration.
- F. None of above. chosen
Provenance (4 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_69a24fcdaeb48190a2d796677e4b3281 |
completed | Feb. 28, 2026, 2:15 a.m. |
| NER | Named-entity recognition | batch_69a25760af348190bf402089c240887d |
completed | Feb. 28, 2026, 2:48 a.m. |
| PD | Predicate disambiguation | batch_69a2564417848190a8a8a38e97348963 |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a2575d8a648190ad8e10d4b04e5e07 |
completed | Feb. 28, 2026, 2:47 a.m. |
Created at: Feb. 28, 2026, 2:20 a.m.