Triple
T29227988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | London Underground bombing |
E740985
|
entity |
| Predicate | targetsInfrastructure |
P42768
|
FINISHED |
| Object | London Underground |
—
|
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: London Underground | Statement: [London Underground bombing, targetsInfrastructure, London Underground]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetsInfrastructure Context triple: [London Underground bombing, targetsInfrastructure, London Underground]
-
A.
targetedInfrastructure
chosen
Indicates that an entity deliberately selected and acted against a specific piece of infrastructure as the focus of its operation or attack.
-
B.
identifiesInfrastructure
Indicates that one entity recognizes, designates, or specifies another entity as infrastructure within a given context.
-
C.
relatedInfrastructure
Indicates that one piece of infrastructure is connected, associated, or functionally related to another infrastructure element.
-
D.
targetsSystems
Indicates that an entity is directed at, attacks, or is intended to affect specific systems.
-
E.
targetsProvision
Indicates that one entity is the intended recipient or beneficiary of a provision, service, or resource supplied 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_69f07cbb12bc81908c1971d9de9a8d2a |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69fcab6e888881908ca9e18660928a40 |
completed | May 7, 2026, 3:10 p.m. |
| PD | Predicate disambiguation | batch_69fc4562a5b88190bad48f083a6dcdfa |
completed | May 7, 2026, 7:55 a.m. |
Created at: April 28, 2026, 12:17 p.m.