Triple
T1602450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2017 Manchester Arena bombing |
E34424
|
entity |
| Predicate | explosiveType |
P21566
|
FINISHED |
| Object | TATP-based bomb |
—
|
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: TATP-based bomb | Statement: [2017 Manchester Arena bombing, explosiveType, TATP-based bomb]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: explosiveType Context triple: [2017 Manchester Arena bombing, explosiveType, TATP-based bomb]
-
A.
explosiveLensType
Indicates the specific design or configuration of the explosive lens used to shape and direct the detonation wave.
-
B.
explosiveDevice
chosen
Indicates the presence or involvement of an object designed to explode or cause an explosion in relation to the associated entities.
-
C.
detonationMethod
Indicates the method or mechanism by which an explosive device is triggered or detonated.
-
D.
numberOfExplosions
Indicates the count of distinct explosion events associated with an entity or situation.
-
E.
bombingMethod
Indicates the method or technique used to carry out a bombing.
- 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_69a885fea6a481909fe83ba6441f1774 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a95b02cd448190be8e3db9a5a7bac0 |
completed | March 5, 2026, 10:29 a.m. |
| PD | Predicate disambiguation | batch_69a907c1cad08190b9728dd557f39aa0 |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:28 p.m.