Triple
T23776711
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Babylon (as prisoner, according to 2 Chronicles) |
E587695
|
entity |
| Predicate | captorOf |
P87093
|
FINISHED |
| Object | Manasseh, king of Judah |
—
|
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: Manasseh, king of Judah | Statement: [Babylon (as prisoner, according to 2 Chronicles), captorOf, Manasseh, king of Judah]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: captorOf Context triple: [Babylon (as prisoner, according to 2 Chronicles), captorOf, Manasseh, king of Judah]
-
A.
captorOfPredecessor
Indicates that one entity held another entity captive, where the captive is the predecessor of a third related entity.
-
B.
capturedAs
chosen
Indicates that one entity has been taken into custody or control by another entity, typically as a prisoner or target.
-
C.
capturedFor
Indicates that one entity has been taken into custody, control, or possession specifically for the benefit, use, or purpose of another entity.
-
D.
capturedUsing
Indicates that something was recorded, obtained, or documented by means of a specified tool, method, or device.
-
E.
capturedBy
Indicates that one entity has been seized, taken into control, or otherwise apprehended by another entity.
- 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_69e2490d245881909028226a1393d624 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1c46c1ea881908dfdc305e58516db |
completed | April 29, 2026, 8:42 a.m. |
| PD | Predicate disambiguation | batch_69f155f79e34819080f9ddb972b34deb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:16 p.m.