Triple
T6989348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abuja Treaty |
E162044
|
entity |
| Predicate | dividesIntegrationInto |
P59416
|
FINISHED |
| Object | six stages |
—
|
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: six stages | Statement: [Abuja Treaty, dividesIntegrationInto, six stages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dividesIntegrationInto Context triple: [Abuja Treaty, dividesIntegrationInto, six stages]
-
A.
parallelDivision
Indicates that one entity is divided or partitioned in a way that runs parallel to the division or partitioning of another entity.
-
B.
dividedBetween
Indicates that something is partitioned or shared among two or more distinct entities or groups.
-
C.
divisionRenamedFrom
Indicates that a division currently known by one name was previously known by another specified name.
-
D.
integrates
Indicates that one entity combines or brings together another entity or set of entities into a unified, functioning whole.
-
E.
relatedDivide
chosen
Indicates that one entity divides or partitions another entity in a way that is contextually or relationally significant, rather than purely numerical.
- 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_69c68856d7808190ab33ee914640281b |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6dbbee0e881909f78370856594cd6 |
completed | March 27, 2026, 7:34 p.m. |
| PD | Predicate disambiguation | batch_69c6d7c4a18881908d267137daed828b |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:32 p.m.