Triple
T411246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United Nations Partition Plan for Palestine |
E9493
|
entity |
| Predicate | resolutionNumber |
P2285
|
FINISHED |
| Object | 181 |
—
|
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: 181 | Statement: [United Nations Partition Plan for Palestine, resolutionNumber, 181]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: resolutionNumber Context triple: [United Nations Partition Plan for Palestine, resolutionNumber, 181]
-
A.
resolution
Indicates the act of formally deciding, settling, or expressing a determined stance on an issue, often through an official decision or statement.
-
B.
resolutionClass
Indicates the category or type of resolution applied to address or conclude a particular issue, conflict, or process.
-
C.
UNResolutionNumber
chosen
Indicates the specific numerical identifier assigned to a United Nations resolution that references or governs the related entities or actions.
-
D.
titleNumber
Indicates the numerical designation or sequence number assigned to a title within an ordered set of titles.
-
E.
resolves
Indicates that one entity successfully finds a solution, answer, or outcome for a problem, conflict, or uncertainty involving another entity.
- 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_69a2e80111fc8190961d5b7c6154123f |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2ed31681c8190ac32334562fb17fd |
completed | Feb. 28, 2026, 1:27 p.m. |
| PD | Predicate disambiguation | batch_69a2e9737694819080fde9adcc1aa4d4 |
completed | Feb. 28, 2026, 1:11 p.m. |
Created at: Feb. 28, 2026, 1:09 p.m.