Triple
T6839996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeddah Agreement of 1970 |
E157546
|
entity |
| Predicate | betweenParty |
P52873
|
FINISHED |
| Object | royalist faction in North Yemen |
—
|
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: royalist faction in North Yemen | Statement: [Jeddah Agreement of 1970, betweenParty, royalist faction in North Yemen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: betweenParty Context triple: [Jeddah Agreement of 1970, betweenParty, royalist faction in North Yemen]
-
A.
arePartyTo
chosen
Indicates that the entities are participants or signatories in the same agreement, contract, or legal arrangement.
-
B.
negotiatingParty
Indicates that an entity is actively involved as a participant in a negotiation process with another entity.
-
C.
participatingParty
Indicates that an entity is involved as a participant in a particular event, activity, or transaction.
-
D.
partnerInConflictResolutionWith
Indicates that two entities collaborate as partners in resolving a specific conflict or dispute.
-
E.
otherSignificantParty
Indicates that an entity has another important associated party, such as a key counterpart, partner, or involved participant in a relationship or transaction.
- 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_69c6882c53608190b99aebef079b23bd |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d6b2ee248190991c3e827be75bb7 |
completed | March 27, 2026, 7:12 p.m. |
| PD | Predicate disambiguation | batch_69c6d09f90648190bc0a462c7d59de1b |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:19 p.m.