Triple
T3036456
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geneva Accords |
E83021
|
entity |
| Predicate | establishedDemarcationLine |
P21958
|
FINISHED |
| Object | 17th parallel in Vietnam |
—
|
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: 17th parallel in Vietnam | Statement: [Geneva Accords, establishedDemarcationLine, 17th parallel in Vietnam]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: establishedDemarcationLine Context triple: [Geneva Accords, establishedDemarcationLine, 17th parallel in Vietnam]
-
A.
demarcationType
Indicates the specific way in which a boundary or separation between entities is defined, marked, or categorized.
-
B.
divisionLine
chosen
Indicates a boundary or separating line that divides one area, group, or portion from another.
-
C.
borderPoint
Indicates a point that lies on the boundary between two regions or entities.
-
D.
lineStandard
Indicates that one entity is a standard or reference specification that defines or governs the characteristics or requirements of a particular line (such as a product line, production line, or service line).
-
E.
frontLineBetween
Indicates that a boundary or line of direct confrontation exists separating two opposing sides or regions.
- 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_69ad8b2298908190a7cb4e9bdbf064d0 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9b2cd4988190b52fe3616ecbe9ef |
completed | March 8, 2026, 3:52 p.m. |
| PD | Predicate disambiguation | batch_69ad961e2a408190afb1759132701305 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3:01 p.m.