Triple
T25563977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erdut |
E640785
|
entity |
| Predicate | agreementNameDerivedFrom |
P116190
|
FINISHED |
| Object | Erdut Agreement |
—
|
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: Erdut Agreement | Statement: [Erdut, agreementNameDerivedFrom, Erdut Agreement]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: agreementNameDerivedFrom Context triple: [Erdut, agreementNameDerivedFrom, Erdut Agreement]
-
A.
treatyNameDerivedFrom
chosen
Indicates that the name of a treaty is derived from, or based on, another specified source such as a place, person, event, or document.
-
B.
signedAgreementName
Indicates that an entity has signed an agreement identified by a specific name.
-
C.
agreementOrigin
Indicates that an agreement originates from, is derived from, or is based on a specified source or prior arrangement.
-
D.
formedByAgreementWith
Indicates that something comes into existence or is established as a direct result of a formal agreement between parties.
-
E.
basedOnAgreementWith
Indicates that something exists, is done, or is determined on the basis of a prior agreement or accord between the involved parties.
- 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_69e75dc1beb08190bac7d76b8d6e7bc4 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f8fb94b48190b135b603667279a7 |
completed | May 2, 2026, 1:15 p.m. |
| PD | Predicate disambiguation | batch_69f468421ba08190880eac99135e5970 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 3:48 p.m.