Triple
T38400986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zalambessa |
E900897
|
entity |
| Predicate | borderTownFacing |
P107933
|
FINISHED |
| Object | Eritrea |
—
|
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: Eritrea | Statement: [Zalambessa, borderTownFacing, Eritrea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderTownFacing Context triple: [Zalambessa, borderTownFacing, Eritrea]
-
A.
borderCountrySide
Indicates that one country shares a land border with the side or region of another country.
-
B.
borderTownAcrossBorder
chosen
Indicates that a town lies on one side of a border directly opposite or adjacent to a town on the other side of that border.
-
C.
borderTownAccess
Indicates that an entity has permission or the ability to enter, use, or pass through a town located on or near a border.
-
D.
borderStreet
Indicates that a street forms or lies along the boundary between two geographic areas or properties.
-
E.
borderTownTerminus
Indicates a location that serves as the endpoint or terminal stop of a route situated in or at a border town.
- 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_69f76e6071a081909eea7a670d21420c |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a00332eaa0c8190a69ea895576bb0ee |
completed | May 10, 2026, 7:26 a.m. |
| PD | Predicate disambiguation | batch_6a0032b2ea80819083b89ebb88165933 |
completed | May 10, 2026, 7:24 a.m. |
Created at: May 3, 2026, 4:31 p.m.