Triple
T36400723
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abyei |
E896615
|
entity |
| Predicate | referendumIssue |
P38649
|
FINISHED |
| Object | whether to join Sudan or South Sudan |
—
|
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: whether to join Sudan or South Sudan | Statement: [Abyei, referendumIssue, whether to join Sudan or South Sudan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: referendumIssue Context triple: [Abyei, referendumIssue, whether to join Sudan or South Sudan]
-
A.
referendumRelated
Indicates a relationship where something is connected to, associated with, or arising from a referendum process or its outcomes.
-
B.
subjectOfReferendum
chosen
Indicates that something is the issue, proposal, or matter being decided upon in a referendum.
-
C.
referendumEvent
Indicates that an event is a referendum, i.e., a formal process in which eligible participants vote directly to accept or reject a specific proposal or decision.
-
D.
typeOfReferendum
Indicates the specific category or kind of referendum that is being held or referred to.
-
E.
heldReferendum
Indicates that an entity organized and conducted a referendum, typically allowing eligible participants to vote directly on a specific issue or proposal.
- 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_69f76e53b81081908d3b81860593f38a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69feafa1ba0081909013800b85a9f613 |
completed | May 9, 2026, 3:53 a.m. |
| PD | Predicate disambiguation | batch_69feae58d62c81909d031f3df8992883 |
completed | May 9, 2026, 3:47 a.m. |
Created at: May 3, 2026, 4:10 p.m.