Triple
T30448227
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Libyan Arab Jamahiriya emblem |
E774638
|
entity |
| Predicate | usedUnderLeader |
P34216
|
FINISHED |
| Object | Muammar Gaddafi |
—
|
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: Muammar Gaddafi | Statement: [Libyan Arab Jamahiriya emblem, usedUnderLeader, Muammar Gaddafi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedUnderLeader Context triple: [Libyan Arab Jamahiriya emblem, usedUnderLeader, Muammar Gaddafi]
-
A.
establishedUnderLeader
Indicates that an entity was founded, created, or formally established during the tenure or authority of a specific leader.
-
B.
implementedUnderLeader
chosen
Indicates that an action, project, or policy was carried out under the authority, direction, or tenure of a specific leader.
-
C.
servedUnderLeader
Indicates that one entity held a position or role subordinate to, and operating under the authority or command of, another specified leader.
-
D.
supportedLeader
Indicates that one entity actively backed, endorsed, or provided assistance to a particular leader.
-
E.
namedByLeader
Indicates that an entity has been given its name by a specific leader or person in authority.
- 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_69f22493ef9c8190ae8c2afcb7f994c8 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f686c1b7988190a0750c687c5d0dd1 |
completed | May 2, 2026, 11:20 p.m. |
| PD | Predicate disambiguation | batch_69f678d2196c8190b9d0d2fcd47cc539 |
completed | May 2, 2026, 10:21 p.m. |
Created at: April 29, 2026, 8:09 p.m.