Triple
T31903097
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2008 Mumbai attacks |
E814475
|
entity |
| Predicate | coordinatedAttackOn |
P178086
|
FINISHED |
| Object | Taj Mahal Palace Hotel |
—
|
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: Taj Mahal Palace Hotel | Statement: [2008 Mumbai attacks, coordinatedAttackOn, Taj Mahal Palace Hotel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coordinatedAttackOn Context triple: [2008 Mumbai attacks, coordinatedAttackOn, Taj Mahal Palace Hotel]
-
A.
coordinatedAttacksAlsoTargeted
Indicates that in a set of coordinated attacks, the same target was also attacked as part of those coordinated actions.
-
B.
plannedAttackWith
Indicates that one entity has prepared or organized an attack using or involving another entity as the means or instrument of that attack.
-
C.
plannedAttack
Indicates that an entity has intentionally prepared and organized an attack against a target.
-
D.
numberOfCoordinatedAttacks
Indicates the total count of coordinated attacks carried out or associated with the given entity or event.
-
E.
cooperationAgainst
Indicates a collaborative relationship in which two or more entities work together in opposition to a shared target or adversary.
- 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_69f707f7959881908f037f0d6b1d0c36 |
completed | May 3, 2026, 8:31 a.m. |
| PD | Predicate disambiguation | batch_69f700fc274c8190a128593dc7c7abd0 |
completed | May 3, 2026, 8:02 a.m. |
| PDg | Predicate description generation | batch_69f707f380388190954b79d52a321921 |
completed | May 3, 2026, 8:31 a.m. |
Created at: May 1, 2026, midnight