Triple
T26778720
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | July 25, 2019 Trump–Zelenskyy phone call |
E670190
|
entity |
| Predicate | summaryReleaseDate |
P161487
|
FINISHED |
| Object | 2019-09-25 |
—
|
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: 2019-09-25 | Statement: [July 25, 2019 Trump–Zelenskyy phone call, summaryReleaseDate, 2019-09-25]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: summaryReleaseDate Context triple: [July 25, 2019 Trump–Zelenskyy phone call, summaryReleaseDate, 2019-09-25]
-
A.
businessReleaseDate
Indicates the date on which a product, service, or offering is officially made available for business or commercial use.
-
B.
consoleReleaseDate
Indicates the calendar date on which a particular game console was first released to the public.
-
C.
ukReleaseDate
Indicates the date on which something is released or made publicly available in the United Kingdom.
-
D.
volumeReleased
Indicates that a specific volume (such as a book, issue, or installment) has been officially released or made publicly available.
-
E.
studioRelease
Indicates that a work (such as a film, album, or game) is officially released or distributed by a particular studio.
- 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_69eeb31c925881909b597f6e40056d28 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f6197855f481909d48a0fe694b8c53 |
completed | May 2, 2026, 3:34 p.m. |
| PD | Predicate disambiguation | batch_69f611ad2eb48190ac1ed0090f13f7a9 |
completed | May 2, 2026, 3:01 p.m. |
| PDg | Predicate description generation | batch_69f6142a0b988190b404d078f73c3cb9 |
completed | May 2, 2026, 3:11 p.m. |
Created at: April 27, 2026, 4:07 a.m.