Triple
T48365
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Home Owners' Loan Corporation |
E949
|
entity |
| Predicate | usedInstrument |
P933
|
FINISHED |
| Object | federally backed mortgage refinancing |
—
|
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: federally backed mortgage refinancing | Statement: [Home Owners' Loan Corporation, usedInstrument, federally backed mortgage refinancing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedInstrument Context triple: [Home Owners' Loan Corporation, usedInstrument, federally backed mortgage refinancing]
-
A.
usesInstrument
chosen
Indicates that an agent performs an action by employing a specific instrument or tool as the means to carry it out.
-
B.
reliesOnInstrument
Indicates that an action or process depends on or is carried out using a particular instrument or tool.
-
C.
instrument
Indicates that an action is carried out using a particular tool, means, or implement as its instrument.
-
D.
createdInstrument
Indicates that an entity brought into existence or produced a particular instrument or tool.
-
E.
usedWeapon
Indicates that an entity employed a specific weapon as the means or tool to carry out an action or event.
- 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_69a2480baefc81909951b14058479aa2 |
completed | Feb. 28, 2026, 1:42 a.m. |
| NER | Named-entity recognition | batch_69a24c1a5c14819088748317a3f262c8 |
completed | Feb. 28, 2026, 1:59 a.m. |
| PD | Predicate disambiguation | batch_69a24abe7cb481908d969e54032f6c75 |
completed | Feb. 28, 2026, 1:54 a.m. |
Created at: Feb. 28, 2026, 1:47 a.m.