Triple
T1189577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Senkaku Islands |
E25325
|
entity |
| Predicate | underUSControlFrom |
P21508
|
FINISHED |
| Object | 1945 |
—
|
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: 1945 | Statement: [Senkaku Islands, underUSControlFrom, 1945]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: underUSControlFrom Context triple: [Senkaku Islands, underUSControlFrom, 1945]
-
A.
under
Indicates that one entity is positioned below or beneath another entity, often implying vertical alignment or coverage.
-
B.
teamStateControlled
Indicates that a team is under the authority, governance, or regulatory control of a particular state or governmental entity.
-
C.
isUsedUnder
Indicates that one entity is utilized or applied within the context, conditions, or framework defined by another entity.
-
D.
timeUnderControlOfUnitedStates
chosen
Indicates that, during a specified time period, the referenced entity was under the political or administrative control of the United States.
-
E.
familyControlled
Indicates that an entity is owned or effectively governed by one or more members of the same family, who hold decisive control over its decisions or operations.
- 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_69a49427d98881908646d6c63b8cea1e |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bd57c3c481908bdca483fcaa3297 |
completed | March 1, 2026, 10:27 p.m. |
| PD | Predicate disambiguation | batch_69a4bb5bacc481909e8dfd5215e4711a |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:45 p.m.