Triple
T31712996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ogaden National Liberation Front |
E809377
|
entity |
| Predicate | operatesNearBorderWith |
P61305
|
FINISHED |
| Object | Somalia |
—
|
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: Somalia | Statement: [Ogaden National Liberation Front, operatesNearBorderWith, Somalia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesNearBorderWith Context triple: [Ogaden National Liberation Front, operatesNearBorderWith, Somalia]
-
A.
operatedAlongBorderWith
Indicates that an operation or activity was carried out in proximity to, or following the line of, a shared border between two entities.
-
B.
locatedNearStateBorderWith
chosen
Indicates that one entity is situated geographically close to the border of a specified state.
-
C.
connectsToCountryBorder
Indicates that one entity is directly adjacent to and touches the border of a specified country.
-
D.
borderingCountryInteraction
Indicates interactions, relationships, or exchanges that occur specifically between countries that share a common border.
-
E.
hasCountryBorderWith
Indicates that two countries share a common land or maritime boundary.
- 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_69f348df4e048190a4a5a9932ada78d6 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69ffc1550cb481908628e446d9b67f7b |
completed | May 9, 2026, 11:20 p.m. |
| PD | Predicate disambiguation | batch_69ffc10a74708190ae90e2c378791f70 |
completed | May 9, 2026, 11:19 p.m. |
Created at: April 30, 2026, 11:16 p.m.