Triple
T1648394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spending Review |
E35634
|
entity |
| Predicate | informedBy |
P22819
|
FINISHED |
| Object | Office for Budget Responsibility forecasts |
—
|
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: Office for Budget Responsibility forecasts | Statement: [Spending Review, informedBy, Office for Budget Responsibility forecasts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: informedBy Context triple: [Spending Review, informedBy, Office for Budget Responsibility forecasts]
-
A.
providesInformationIn
Indicates that one entity supplies or conveys information within or through another entity or context.
-
B.
believedProvidedBy
Indicates that something is thought or assumed to have been supplied or made available by a particular source or provider.
-
C.
reliedOn
chosen
Indicates that one entity depends on another for support, resources, or functionality.
-
D.
knownFrom
Indicates that one entity is aware of, has learned about, or recognizes another entity through a specified source, context, or medium.
-
E.
believedBy
Indicates that a particular proposition, statement, or entity is held to be true or accepted as real by a specified believer.
- 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_69a8860568888190a32cd9f70acbba42 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aaa0fbe984819084f8daee81ca9b67 |
completed | March 6, 2026, 9:40 a.m. |
| PD | Predicate disambiguation | batch_69a907ce4dd881909168a1e99505d4ec |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:29 p.m.