Triple
T6357270
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taif Agreement |
E143022
|
entity |
| Predicate | signatoryGroup |
P55779
|
FINISHED |
| Object | Muslim political leaders in Lebanon |
—
|
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: Muslim political leaders in Lebanon | Statement: [Taif Agreement, signatoryGroup, Muslim political leaders in Lebanon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: signatoryGroup Context triple: [Taif Agreement, signatoryGroup, Muslim political leaders in Lebanon]
-
A.
signatoryType
Indicates the specific role or category of a party that has signed or formally agreed to a document, contract, or agreement.
-
B.
signatoryOrganization
Indicates that an organization has formally signed or endorsed an agreement, document, or commitment.
-
C.
signatoryBloc
Indicates that an entity is a member of, or aligned with, a specific bloc or group that has jointly signed or endorsed an agreement, treaty, or document.
-
D.
hasSignatories
Indicates that one or more parties have formally signed or endorsed an agreement, document, or instrument.
-
E.
collectiveSignatories
chosen
Indicates that multiple entities jointly sign or endorse the same document, agreement, or statement as a group.
- 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_69c008d7a9c4819098d647ec47776917 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c067f37d0881909289bafb09e29298 |
completed | March 22, 2026, 10:06 p.m. |
| PD | Predicate disambiguation | batch_69c060ec091c8190912aac44e1b8b1c9 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:32 p.m.