Triple
T22029607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | in-person application at IRS Taxpayer Assistance Center |
E544050
|
entity |
| Predicate | appointmentScheduledVia |
P146337
|
FINISHED |
| Object | IRS appointment phone line |
—
|
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: IRS appointment phone line | Statement: [in-person application at IRS Taxpayer Assistance Center, appointmentScheduledVia, IRS appointment phone line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appointmentScheduledVia Context triple: [in-person application at IRS Taxpayer Assistance Center, appointmentScheduledVia, IRS appointment phone line]
-
A.
appointmentBy
Indicates that one entity is appointed or designated to a role, position, or task by another entity.
-
B.
appointmentTerm
Indicates the duration or specific period for which an appointment, position, or role is held.
-
C.
appointmentType
Indicates the specific category or nature of an appointment associated with an entity or event.
-
D.
appointmentOnAdviceOf
Indicates that an appointment or selection of someone to a position is made based on the recommendation, counsel, or formal advice of another person or authority.
-
E.
appointmentBody
Indicates that one entity serves as the main content or body text associated with a particular appointment.
- F. None of above. chosen
Provenance (4 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_69e11e2f98c8819083e11eab90942a78 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127ebf6d48190b84e7a45bbf9049c |
completed | April 28, 2026, 9:34 p.m. |
| PD | Predicate disambiguation | batch_69e6f63b0d048190b241622759aab9de |
completed | April 21, 2026, 3:59 a.m. |
| PDg | Predicate description generation | batch_69e6fad4a540819096cdd5ea08527220 |
completed | April 21, 2026, 4:19 a.m. |
Created at: April 16, 2026, 8:24 p.m.