Triple
T8225980
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2016 Brussels bombings |
E192172
|
entity |
| Predicate | suspectedCell |
P81730
|
FINISHED |
| Object | same network as Paris attackers |
—
|
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: same network as Paris attackers | Statement: [2016 Brussels bombings, suspectedCell, same network as Paris attackers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: suspectedCell Context triple: [2016 Brussels bombings, suspectedCell, same network as Paris attackers]
-
A.
cellType
Indicates the classification relationship that specifies what type of cell an entity is or is associated with.
-
B.
susceptibleTo
Indicates that one entity is vulnerable or likely to be affected, harmed, or influenced by another entity or factor.
-
C.
cellStates
Indicates the various conditions or phases that a cell can be in at a given time.
-
D.
numberOfSuspectedCases
Indicates the quantity of cases that are believed or suspected to exist but are not yet confirmed.
-
E.
suspectedSupporter
Indicates that one entity is believed or suspected to support, assist, or be aligned with another entity, but this support is not confirmed.
- 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_69ca82c9a8ac81908b011c38698456e4 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb77fc10f48190b7e241c89885a478 |
completed | March 31, 2026, 7:30 a.m. |
| PD | Predicate disambiguation | batch_69cb36af41e081909dee92b9bc4947f1 |
completed | March 31, 2026, 2:51 a.m. |
| PDg | Predicate description generation | batch_69cb4d9b03108190a6785834f21ff75e |
completed | March 31, 2026, 4:29 a.m. |
Created at: March 30, 2026, 5:45 p.m.