Triple
T31903128
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2008 Mumbai attacks |
E814475
|
entity |
| Predicate | capturedAttacker |
P172714
|
FINISHED |
| Object | Ajmal Kasab |
—
|
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: Ajmal Kasab | Statement: [2008 Mumbai attacks, capturedAttacker, Ajmal Kasab]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capturedAttacker Context triple: [2008 Mumbai attacks, capturedAttacker, Ajmal Kasab]
-
A.
capturedOff
Indicates that one entity has taken another entity away or into custody, removing it from its original location or control.
-
B.
belligerentSideAfterCapture
Indicates the party or side that an entity belongs to after it has been captured in a conflict or competitive interaction.
-
C.
mainAttacker
Indicates that an entity is the primary or leading aggressor responsible for initiating or carrying out an attack against another entity.
-
D.
capturedForce
Indicates that one entity has taken control of another entity or group through force, restraint, or coercive action.
-
E.
capturedCommander
Indicates that one party has taken a military commander from another party into custody or control.
- 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_69f348f04d7881909537fc9e7cbc670e |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b1b18c30819098ac3103f54ad310 |
completed | May 3, 2026, 2:23 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
| PDg | Predicate description generation | batch_69f6af7d92008190aead47eaae8cc091 |
completed | May 3, 2026, 2:14 a.m. |
Created at: May 1, 2026, midnight