Triple
T29113389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eleazar ben Shammua |
E736975
|
entity |
| Predicate | activeAfterEvent |
P103230
|
FINISHED |
| Object | Bar Kokhba revolt |
—
|
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: Bar Kokhba revolt | Statement: [Eleazar ben Shammua, activeAfterEvent, Bar Kokhba revolt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: activeAfterEvent Context triple: [Eleazar ben Shammua, activeAfterEvent, Bar Kokhba revolt]
-
A.
activeAfter
chosen
Indicates that one entity becomes active only after another specified event, state, or time has occurred.
-
B.
usedAfterEventFor
Indicates that one entity is used only after a specified event has occurred or been completed.
-
C.
activeInEvent
Indicates that an entity participates in or is involved in carrying out actions within a particular event.
-
D.
activeBefore
Indicates that one entity is active or in effect prior to the time another entity becomes active or in effect.
-
E.
settingAfterEvent
Indicates that a particular setting or state occurs subsequent to, and as a result of or in temporal sequence with, a specified event.
- 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_69f077ed54e08190bb02a744e8121a66 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f6d0d46aec819091edf97324d793ac |
completed | May 3, 2026, 4:36 a.m. |
| PD | Predicate disambiguation | batch_69f6cfe2183481908ae4e85a59c66f69 |
completed | May 3, 2026, 4:32 a.m. |
Created at: April 28, 2026, 11:20 a.m.