Triple
T29534705
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Koza |
E749305
|
entity |
| Predicate | hasCloseHistoricalTiesTo |
P150178
|
FINISHED |
| Object | U.S. military bases |
—
|
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: U.S. military bases | Statement: [Koza, hasCloseHistoricalTiesTo, U.S. military bases]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCloseHistoricalTiesTo Context triple: [Koza, hasCloseHistoricalTiesTo, U.S. military bases]
-
A.
hasHistoricalTieTo
Indicates a relationship where one entity is historically connected or linked to another through past events, associations, or influences.
-
B.
hasNegativeHistoricalAssociation
Indicates that one entity is historically linked to another in a way that is viewed as harmful, problematic, or disreputable.
-
C.
hasSharedBorderHistoryWith
Indicates that two entities have a history of sharing a common border or boundary at some point in time.
-
D.
hasHeritageConnectionWith
Indicates a relationship where two entities are linked through shared, inherited, or culturally transmitted heritage or ancestry.
-
E.
historicalRelationsWith
chosen
Indicates a relationship where one entity has documented or recognized connections, interactions, or associations with another entity in the past.
- 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_69f0bd47abb081909bd6e6a33d770fd8 |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f7764ab1fc81909f9348db87bd7692 |
completed | May 3, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69f76905d9c88190b1ee810bc9ab644f |
completed | May 3, 2026, 3:25 p.m. |
Created at: April 28, 2026, 4:56 p.m.