Triple
T30485597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Togo–Ghana border region |
E775709
|
entity |
| Predicate | borderSuccessorState |
P16434
|
FINISHED |
| Object | British Togoland |
—
|
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: British Togoland | Statement: [Togo–Ghana border region, borderSuccessorState, British Togoland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderSuccessorState Context triple: [Togo–Ghana border region, borderSuccessorState, British Togoland]
-
A.
successorBorder
chosen
Indicates that one entity’s border directly follows or replaces another entity’s border in a sequence or progression.
-
B.
borderStateDestination
Indicates that the destination state shares a common border with another referenced state.
-
C.
successorStateFlag
Indicates that a particular state directly follows another state in a defined sequence or process.
-
D.
successorStateOver
Indicates that one state directly follows another in an ordered progression or sequence over a given dimension or context.
-
E.
successorState
Indicates that one state directly follows another as the immediate next state in a sequence or process.
- 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_69f22497f91c8190afa7165bc900accd |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fe7eb4b8348190bb19d35766189ed4 |
completed | May 9, 2026, 12:24 a.m. |
| PD | Predicate disambiguation | batch_69fe7c35d2148190ab952e54feda1e76 |
completed | May 9, 2026, 12:13 a.m. |
Created at: April 29, 2026, 8:13 p.m.