Triple
T3705643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pan Am Flight 103 |
E80885
|
entity |
| Predicate | perpetratorAlleged |
P21177
|
FINISHED |
| Object | Libyan intelligence operatives |
—
|
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: Libyan intelligence operatives | Statement: [Pan Am Flight 103, perpetratorAlleged, Libyan intelligence operatives]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: perpetratorAlleged Context triple: [Pan Am Flight 103, perpetratorAlleged, Libyan intelligence operatives]
-
A.
suspectedPerpetrator
chosen
Indicates that an entity is believed or alleged to be the person responsible for committing a particular harmful or illegal act.
-
B.
perpetratedBy
Indicates that an action, event, or wrongdoing was carried out or caused by a particular agent or entity.
-
C.
perpetratorAllegiance
Indicates that the perpetrator is affiliated with, loyal to, or acting on behalf of a particular group, organization, or cause.
-
D.
allegedActor
Indicates that the subject is claimed or accused to be the actor responsible for a particular action or event, without confirming that the claim is true.
-
E.
perpetratorNationality
Indicates the country or nationality to which a perpetrator of an act, crime, or harmful event belongs.
- 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_69ad8b1793888190a5f70e4b21dc05a1 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adc54ce1788190ac000793cbdaba48 |
completed | March 8, 2026, 6:51 p.m. |
| PD | Predicate disambiguation | batch_69adc041a8608190a2d543dab6d2ef6c |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:33 p.m.