Triple
T31547584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Philadelphia Office of Property Assessment |
E804909
|
entity |
| Predicate | typeOfTaxInvolved |
P3166
|
FINISHED |
| Object | real estate tax |
—
|
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: real estate tax | Statement: [Philadelphia Office of Property Assessment, typeOfTaxInvolved, real estate tax]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfTaxInvolved Context triple: [Philadelphia Office of Property Assessment, typeOfTaxInvolved, real estate tax]
-
A.
taxType
chosen
Indicates the specific category or classification of tax that applies to an entity, transaction, or amount.
-
B.
typeOfTaxChange
Indicates a relationship where one entity represents a specific kind or category of tax modification described or classified by another entity.
-
C.
taxOn
Indicates that one entity imposes or applies a tax on another entity or item.
-
D.
taxationMethod
Indicates the specific way or system by which taxes are calculated, collected, or applied in a given context.
-
E.
taxRate
Indicates the percentage or proportion of a taxable amount that is imposed as tax in a given context.
- 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_69f348d11a048190a65eb8384a3754ac |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69ffe613c03481909f3043ec8bf0bed9 |
completed | May 10, 2026, 1:57 a.m. |
| PD | Predicate disambiguation | batch_69ffe4a73fb4819091600725a443981a |
completed | May 10, 2026, 1:51 a.m. |
Created at: April 30, 2026, 10:09 p.m.