Triple
T2979788
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treaty of Bucharest (1913) |
E80481
|
entity |
| Predicate | awardedRegion |
P20294
|
FINISHED |
| Object | Southern Dobruja to Romania |
—
|
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: Southern Dobruja to Romania | Statement: [Treaty of Bucharest (1913), awardedRegion, Southern Dobruja to Romania]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: awardedRegion Context triple: [Treaty of Bucharest (1913), awardedRegion, Southern Dobruja to Romania]
-
A.
eligibleRegion
Indicates the geographic area within which something (such as an offer, service, or rule) is valid, applicable, or permitted.
-
B.
hasAwardedArea
chosen
Indicates that one entity has formally granted or designated a specific area or territory to another entity.
-
C.
hasRegion
Indicates that an entity includes, contains, or is associated with a specific geographic or administrative region as part of its scope or structure.
-
D.
positionAwarded
Indicates that a specific position, role, or title has been formally granted to an entity (such as a person or organization).
-
E.
favoredRegion
Indicates that one region is preferred or given special priority over others in a particular context.
- 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_69ad8b15f6ac8190be5fd16a33edcb4f |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad999cca40819082e2d6d10bdb7872 |
completed | March 8, 2026, 3:45 p.m. |
| PD | Predicate disambiguation | batch_69ad9611fc348190a5d17d237f653f60 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:58 p.m.