Triple
T18445180
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Buonalbergo family |
E450635
|
entity |
| Predicate | allianceStrategy |
P9451
|
FINISHED |
| Object | marital alliances with powerful 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: marital alliances with powerful rulers | Statement: [Buonalbergo family, allianceStrategy, marital alliances with powerful rulers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: allianceStrategy Context triple: [Buonalbergo family, allianceStrategy, marital alliances with powerful rulers]
-
A.
alliancePolicy
Indicates a formal or informal agreement between entities to cooperate or support each other in pursuit of shared goals or mutual interests.
-
B.
allianceType
chosen
Indicates the specific kind or category of alliance relationship that exists between entities.
-
C.
allianceUse
Indicates that one party makes use of, benefits from, or leverages an alliance or allied relationship with another party.
-
D.
alliance
Indicates a formal cooperative relationship between entities who agree to support each other in shared goals or interests.
-
E.
alliancesAround
Indicates that alliances are formed or exist in the vicinity or context of a specified entity or focal point.
- 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_69d8d381d6388190a9e94e9c658174e4 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e51c15127881909d23b6dd45d7ccc9 |
completed | April 19, 2026, 6:16 p.m. |
| PD | Predicate disambiguation | batch_69e469c943a4819094c8fdc5971ad3a7 |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 11:30 a.m.