Triple
T37976443
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IRS Form 720 |
E947436
|
entity |
| Predicate | paperFilingAddressType |
P3330
|
FINISHED |
| Object | depends on taxpayer’s location |
—
|
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: depends on taxpayer’s location | Statement: [IRS Form 720, paperFilingAddressType, depends on taxpayer’s location]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: paperFilingAddressType Context triple: [IRS Form 720, paperFilingAddressType, depends on taxpayer’s location]
-
A.
typeOfAddress
Indicates the specific category or kind of address (e.g., home, work, billing) associated with an entity.
-
B.
addressType
chosen
Indicates the specific kind or category of address associated with an entity (e.g., home, work, billing, or shipping).
-
C.
filingTypeCode
Indicates the specific category or type of filing associated with a submitted document or record.
-
D.
addresseeType
Indicates the role or category of the entity that is the intended recipient or target of a communication or message.
-
E.
placeOfFiling
Indicates the location or jurisdiction where a legal document, case, or claim is formally submitted or recorded.
- 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_69f76ef7db908190bba6086673a32300 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc7b78f9481909f4f8fc2e3fdcde1 |
completed | May 6, 2026, 10:59 p.m. |
| PD | Predicate disambiguation | batch_69fbbd18c9908190928d274f8731dfa8 |
completed | May 6, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:20 p.m.