Triple
T11812471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States–Russia prisoner exchange |
E280906
|
entity |
| Predicate | typeOfDeal |
P101426
|
FINISHED |
| Object | bilateral agreement |
—
|
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: bilateral agreement | Statement: [United States–Russia prisoner exchange, typeOfDeal, bilateral agreement]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfDeal Context triple: [United States–Russia prisoner exchange, typeOfDeal, bilateral agreement]
-
A.
saleType
Indicates the specific category or method by which a sale is conducted or classified (e.g., retail, wholesale, auction).
-
B.
dealContent
Indicates that one entity contains, specifies, or represents the substantive terms, details, or material of a deal or agreement involving another entity.
-
C.
subjectOfSale
Indicates that one entity is the item, asset, or right being transferred or offered in a sale transaction involving another entity.
-
D.
typeOfNegotiation
Indicates the specific kind or category of negotiation process that characterizes the interaction between the involved parties.
-
E.
saleTo
Indicates a transaction in which one party sells goods, services, or assets to another party.
- F. None of above. chosen
Provenance (4 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_69d6ab26aae88190b2489efcb2a24234 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a658f918819092c2db05fe2ab0ce |
completed | April 10, 2026, 7:27 a.m. |
| PD | Predicate disambiguation | batch_69d8a24e9a088190aff7932d1ff93dbf |
completed | April 10, 2026, 7:10 a.m. |
| PDg | Predicate description generation | batch_69d8a6574b7081908f7451d2bb233967 |
completed | April 10, 2026, 7:27 a.m. |
Created at: April 8, 2026, 9:42 p.m.