Triple
T284216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NATO Headquarters, Brussels, Belgium |
E5852
|
entity |
| Predicate | moveOfNATOFrom |
P9102
|
FINISHED |
| Object | Paris to Brussels in 1967 |
—
|
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: Paris to Brussels in 1967 | Statement: [NATO Headquarters, Brussels, Belgium, moveOfNATOFrom, Paris to Brussels in 1967]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: moveOfNATOFrom Context triple: [NATO Headquarters, Brussels, Belgium, moveOfNATOFrom, Paris to Brussels in 1967]
-
A.
NATOcode
Indicates that there is a specified NATO (North Atlantic Treaty Organization) code assigned to or associated with an entity.
-
B.
isNATOAllyOf
Indicates that one entity is a member of NATO and has a formal alliance relationship with the other entity within the NATO framework.
-
C.
positionOnNATO
Indicates a country's stance or alignment regarding membership in, support for, or opposition to NATO.
-
D.
EUMemberState
Indicates that an entity is a country that is a member state of the European Union.
-
E.
unificationDate
Indicates the date on which two or more previously separate entities were formally unified into a single entity.
- 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_69a25946a7ac8190a78871c210213272 |
completed | Feb. 28, 2026, 2:56 a.m. |
| NER | Named-entity recognition | batch_69a25e0d789881908d6a9a8d6a0d4a6c |
completed | Feb. 28, 2026, 3:16 a.m. |
| PD | Predicate disambiguation | batch_69a25b795a6c8190944d48e8418e0ccd |
completed | Feb. 28, 2026, 3:05 a.m. |
| PDg | Predicate description generation | batch_69a25c4b773c81908f1017f40b0bfd07 |
completed | Feb. 28, 2026, 3:08 a.m. |
Created at: Feb. 28, 2026, 3:02 a.m.