Triple
T3740340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Troubled Asset Relief Program |
E79682
|
entity |
| Predicate | initialStrategy |
P13064
|
FINISHED |
| Object | purchase troubled mortgage-related assets |
—
|
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: purchase troubled mortgage-related assets | Statement: [Troubled Asset Relief Program, initialStrategy, purchase troubled mortgage-related assets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: initialStrategy Context triple: [Troubled Asset Relief Program, initialStrategy, purchase troubled mortgage-related assets]
-
A.
earlyStrategy
Indicates that an entity adopts or implements a strategy at an early stage or time relative to a process, event, or development.
-
B.
initialOpening
Indicates the first or earliest instance in which something is opened, begun, or made accessible.
-
C.
strategyType
Indicates the specific kind or category of strategy associated with an entity or action.
-
D.
usesStrategy
chosen
Indicates that an entity intentionally applies a particular strategy or method to achieve a goal or perform an action.
-
E.
initialOutcome
Indicates the result or state that first occurs at the beginning of a process, event, or interaction, before any subsequent changes or outcomes.
- 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_69ad8b115610819095b02007da5ca3cb |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcb5344fc8190b183aca5c04e3bcc |
completed | March 8, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_69adc048f28c819092bed16a95a3cac1 |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:34 p.m.