Triple
T7941374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Form 940 |
E184398
|
entity |
| Predicate | dueDateRule |
P8546
|
FINISHED |
| Object | due by January 31 following the end of the calendar year |
—
|
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: due by January 31 following the end of the calendar year | Statement: [Form 940, dueDateRule, due by January 31 following the end of the calendar year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dueDateRule Context triple: [Form 940, dueDateRule, due by January 31 following the end of the calendar year]
-
A.
endedDueTo
Indicates that an event, process, or state came to a conclusion specifically because of a particular cause or condition.
-
B.
hasDeadline
chosen
Indicates that an entity is associated with a specific due date or time by which it must be completed or fulfilled.
-
C.
endDate
Indicates the point in time at which an event, state, or relationship stops being valid or comes to a conclusion.
-
D.
durationDependsOn
Indicates that the length of time of one event or state is determined or influenced by another event, condition, or factor.
-
E.
finalDeliveryDate
Indicates the date on which the last or ultimate delivery in a sequence of deliveries is scheduled or actually occurs.
- 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_69ca8291c2008190b1b8832c87814bcf |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3b0c16b8819093c5d1719cd65ee3 |
completed | March 31, 2026, 3:10 a.m. |
| PD | Predicate disambiguation | batch_69cae93526d081909303265bf60419fd |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 5:09 p.m.