Triple
T28653572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CPA of Accra |
E725265
|
entity |
| Predicate | mandatedPresenceOf |
P83557
|
FINISHED |
| Object | United Nations Mission in Liberia |
—
|
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: United Nations Mission in Liberia | Statement: [CPA of Accra, mandatedPresenceOf, United Nations Mission in Liberia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mandatedPresenceOf Context triple: [CPA of Accra, mandatedPresenceOf, United Nations Mission in Liberia]
-
A.
requiresPresence
Indicates that one entity’s existence, operation, or validity depends on another entity being present or available.
-
B.
meetsInPresenceOf
Indicates that two or more entities meet or interact while another specified entity is present as a witness, chaperone, or contextual participant.
-
C.
isMandatoryFor
Indicates that something is required or compulsory for another thing to occur, be valid, or be completed.
-
D.
isMandatoryIn
chosen
Indicates that the presence or inclusion of one entity is required or compulsory within the context, scope, or configuration of another entity.
-
E.
possiblePresenceIn
Indicates that an entity may be located in, occur in, or exist within a specified place, context, or container, without asserting that it is definitively present there.
- 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.