Triple
T11343209
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Afghan tribal forces |
E268650
|
entity |
| Predicate | alliancePattern |
P8409
|
FINISHED |
| Object | formed temporary alliances with Afghan rulers |
—
|
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: formed temporary alliances with Afghan rulers | Statement: [Afghan tribal forces, alliancePattern, formed temporary alliances with Afghan rulers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alliancePattern Context triple: [Afghan tribal forces, alliancePattern, formed temporary alliances with Afghan rulers]
-
A.
newAlliancePattern
Indicates the formation of a new cooperative or strategic alliance pattern between entities.
-
B.
previousAlliancePattern
chosen
Indicates a recurring or characteristic way in which alliances were formed, structured, or aligned between entities in the past.
-
C.
allianceType
Indicates the specific kind or category of alliance relationship that exists between entities.
-
D.
allianceStructure
Indicates the organizational or relational configuration that defines how members of an alliance are structured and interconnected.
-
E.
allianceUse
Indicates that one party makes use of, benefits from, or leverages an alliance or allied relationship with another party.
- 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_69d6aacb1f0881908c84a349fd1be047 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d80148e2048190a716b515d78efdd1 |
completed | April 9, 2026, 7:43 p.m. |
| PD | Predicate disambiguation | batch_69d7e6f8aeb4819080476f16a69b2ee3 |
completed | April 9, 2026, 5:50 p.m. |
Created at: April 8, 2026, 9:33 p.m.