Triple
T31407433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Afghanistan–Iran border |
E801169
|
entity |
| Predicate | northernTripointWith |
P13730
|
FINISHED |
| Object | Turkmenistan |
—
|
NE NERFINISHED |
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: Turkmenistan | Statement: [Afghanistan–Iran border, northernTripointWith, Turkmenistan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: northernTripointWith Context triple: [Afghanistan–Iran border, northernTripointWith, Turkmenistan]
-
A.
southernTripointWith
Indicates a relationship where one entity forms the southernmost tripoint boundary shared with two other entities.
-
B.
hasTripoint
chosen
Indicates that three distinct regions, areas, or entities meet or share a common boundary point.
-
C.
northernTownConnected
Indicates that a town located in the northern region is connected (e.g., by roads, transport, or infrastructure) to another place.
-
D.
northernTerminusConnects
Indicates that a route, line, or pathway connects to or ends at a specified location at its northernmost terminus.
-
E.
northernConnection
Indicates a relationship where one entity is connected to another primarily through or via its northern side, direction, or region.
- 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_69f348c0dd648190bf2fd7642f78eb06 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a916d2e08190bafc01cba73b6469 |
completed | May 3, 2026, 1:47 a.m. |
| PD | Predicate disambiguation | batch_69f6a7548eb48190a69b60a3c6ad53b9 |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 30, 2026, 8:34 p.m.