Triple
T26778787
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Article I: Abuse of Power |
E670191
|
entity |
| Predicate | relatedCall |
P86749
|
FINISHED |
| Object | July 25, 2019 Trump–Zelenskyy phone call |
—
|
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: July 25, 2019 Trump–Zelenskyy phone call | Statement: [Article I: Abuse of Power, relatedCall, July 25, 2019 Trump–Zelenskyy phone call]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedCall Context triple: [Article I: Abuse of Power, relatedCall, July 25, 2019 Trump–Zelenskyy phone call]
-
A.
callsTo
chosen
Indicates that one entity initiates a call or communication action directed toward another entity.
-
B.
relatedCorrespondence
Indicates that there exists a piece of correspondence (such as a letter, email, or message) that is associated with or pertains to the related entity.
-
C.
relatedPass
Indicates that one pass is associated with or connected to another pass in some relevant way.
-
D.
associatedNumber
Indicates a relationship where a specific number is linked or assigned to an entity as its associated value.
-
E.
relatedService
Indicates that one service is connected or associated with another service in a relevant or dependent way.
- 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_69eeb31c925881909b597f6e40056d28 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69fecb4d02f881909a9ee97ce98000d5 |
completed | May 9, 2026, 5:51 a.m. |
| PD | Predicate disambiguation | batch_69fec9846c1c8190b317f0711f0755db |
completed | May 9, 2026, 5:43 a.m. |
Created at: April 27, 2026, 4:07 a.m.