Triple
T1446908
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States in tax litigation |
E31197
|
entity |
| Predicate | roleInDistrictCourtRefundSuit |
P28695
|
FINISHED |
| Object | defendant |
—
|
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: defendant | Statement: [United States in tax litigation, roleInDistrictCourtRefundSuit, defendant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInDistrictCourtRefundSuit Context triple: [United States in tax litigation, roleInDistrictCourtRefundSuit, defendant]
-
A.
hasJudicialDistrict
Indicates that an entity falls within or is associated with a specific judicial district for legal or court-related purposes.
-
B.
usedCourt
Indicates that an entity made use of or participated in legal proceedings within a particular court.
-
C.
affectedCourt
Indicates that a particular court is impacted or influenced by a specified action, decision, or legal matter.
-
D.
courtOrdered
Indicates that an action, condition, or relationship exists because it has been formally mandated or imposed by a court order.
-
E.
trialCourt
Indicates that a legal matter, decision, or proceeding is associated with, handled by, or occurring in a court of first instance (the trial-level court).
- 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_69a499171a28819085b993a3ac78e363 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c558e0e081909802753872374d7b |
completed | March 1, 2026, 11:01 p.m. |
| PD | Predicate disambiguation | batch_69a4c47a840c819083307a65c027a19e |
completed | March 1, 2026, 10:58 p.m. |
| PDg | Predicate description generation | batch_69a4c55508948190922aee3230a4323e |
completed | March 1, 2026, 11:01 p.m. |
Created at: March 1, 2026, 8 p.m.