Triple
T9130465
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mohamed Atta |
E219071
|
entity |
| Predicate | terroristDesignation |
P21106
|
FINISHED |
| Object | al-Qaeda operative |
—
|
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: al-Qaeda operative | Statement: [Mohamed Atta, terroristDesignation, al-Qaeda operative]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: terroristDesignation Context triple: [Mohamed Atta, terroristDesignation, al-Qaeda operative]
-
A.
classifiedAsTerroristBy
chosen
Indicates that an entity has been designated or labeled as a terrorist by a specified authority, organization, or actor.
-
B.
terroristOrganization
Indicates that an entity is recognized as a group that plans, supports, or carries out acts of terrorism.
-
C.
countrySubjectToSanctions
Indicates that a country is currently facing formal sanctions or restrictive measures imposed by another state or international body.
-
D.
coSanctions
Indicates that two or more entities jointly impose or support the same sanction or set of sanctions on a target.
-
E.
hasTerroristAntagonist
Indicates that the subject work features an antagonist who is a terrorist or engages in terrorism.
- 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_69ca83debfc0819095800583e97ab10f |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca8cdafb48190be5e62b15779d771 |
completed | April 1, 2026, 5:10 a.m. |
| PD | Predicate disambiguation | batch_69cc6601d77881908299d58db6e64937 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:18 p.m.