Triple
T31895737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Meredith Whitney |
E814276
|
entity |
| Predicate | madePredictionAbout |
P112259
|
FINISHED |
| Object | Citigroup dividend cut |
—
|
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: Citigroup dividend cut | Statement: [Meredith Whitney, madePredictionAbout, Citigroup dividend cut]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: madePredictionAbout Context triple: [Meredith Whitney, madePredictionAbout, Citigroup dividend cut]
-
A.
predictedIn
Indicates that something has been forecast, anticipated, or estimated to occur within or as part of a specified context, time, or situation.
-
B.
confirmedPredictionOf
Indicates that a previously made prediction about an entity or event has been verified as accurate or true.
-
C.
predictionBy
chosen
Indicates that one entity serves as the source or author of a prediction made about another entity or outcome.
-
D.
predictionType
Indicates the kind or category of prediction being made about an entity or event.
-
E.
saidToHaveMade
Indicates that one entity is reported or alleged to have created, produced, or caused another entity or outcome.
- 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_69f348ef817481908440e2250319bcc8 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b1647918819085ec718e13f9926a |
completed | May 3, 2026, 2:22 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 30, 2026, 11:58 p.m.