Triple
T235264
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U-2 incident of 1960 |
E4495
|
entity |
| Predicate | initialUSResponse |
P8366
|
FINISHED |
| Object | claimed aircraft was a weather research plane |
—
|
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: claimed aircraft was a weather research plane | Statement: [U-2 incident of 1960, initialUSResponse, claimed aircraft was a weather research plane]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: initialUSResponse Context triple: [U-2 incident of 1960, initialUSResponse, claimed aircraft was a weather research plane]
-
A.
enactedInResponseTo
Indicates that one action, policy, or measure was carried out as a direct reaction to a specific prior event, condition, or stimulus.
-
B.
firstMessageTo
Indicates that one entity is the initial sender of a message or communication to another entity.
-
C.
wasResponseTo
Indicates that one event, action, or communication occurred as a direct reply or reaction to a preceding event, action, or communication.
-
D.
firstMessageFrom
Indicates that the related message is the earliest or initial message sent from one entity to another within a given context or conversation.
-
E.
intelligenceUnitUnitedStates
Indicates a relationship where an intelligence unit is part of, operated by, or otherwise affiliated with the United States.
- F. None of above. chosen
Provenance (4 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_69a257363ffc81909757bde7ab3404da |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25cc9ab2c81909af278a07f86aa1e |
completed | Feb. 28, 2026, 3:11 a.m. |
| PD | Predicate disambiguation | batch_69a25b5dc640819092669575731c393f |
completed | Feb. 28, 2026, 3:05 a.m. |
| PDg | Predicate description generation | batch_69a25c2bda788190bcfc0bc94686f9e0 |
completed | Feb. 28, 2026, 3:08 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.