Triple
T1257341
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Low-Income Housing Tax Credit |
E12422
|
entity |
| Predicate | fundingForm |
P59
|
FINISHED |
| Object | foregone federal tax revenue |
—
|
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: foregone federal tax revenue | Statement: [Low-Income Housing Tax Credit, fundingForm, foregone federal tax revenue]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fundingForm Context triple: [Low-Income Housing Tax Credit, fundingForm, foregone federal tax revenue]
-
A.
fundedBy
Indicates that an entity receives financial support or resources from another entity.
-
B.
fundingModel
chosen
Indicates how an entity is financially supported or sustained, such as through specific revenue sources, payment structures, or funding mechanisms.
-
C.
funderType
Indicates the category or kind of organization or individual that provides funding in the relationship.
-
D.
helpedForm
Indicates that one entity contributed significantly to the creation, establishment, or founding of another entity.
-
E.
filingForm
Indicates that an entity submits or completes a specific form or document, typically as part of an official or administrative process.
- 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_69a4933352e08190ac617291985e76c0 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4bfa8cfa08190ac49c437a94a843c |
completed | March 1, 2026, 10:37 p.m. |
| PD | Predicate disambiguation | batch_69a4bb6c977c8190a2bf3e8b67a59beb |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:50 p.m.