Triple
T28653492
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guinean government (alleged support for LURD) |
E725263
|
entity |
| Predicate | accusationsBy |
P15074
|
FINISHED |
| Object | Liberian government under Charles Taylor |
—
|
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: Liberian government under Charles Taylor | Statement: [Guinean government (alleged support for LURD), accusationsBy, Liberian government under Charles Taylor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: accusationsBy Context triple: [Guinean government (alleged support for LURD), accusationsBy, Liberian government under Charles Taylor]
-
A.
associatedWithAccusation
Indicates a relationship where an entity is linked or connected to a specific accusation or charge.
-
B.
accusationType
Indicates the specific category or nature of an accusation made by one party against another.
-
C.
hasAccuser
chosen
Indicates that one entity serves as the accuser of another entity in a dispute, complaint, or allegation.
-
D.
accusationsAddressed
Indicates that previously made accusations have been responded to, dealt with, or otherwise handled by a relevant party.
-
E.
accusationTarget
Indicates that one entity is the object or recipient of an accusation made by another entity.
- 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_69f01d84f5f0819087ab5e6143b14ed7 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651ac855481908e30c3b345d31356 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 4:53 a.m.