Triple
T11755826
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Supreme Court affirmed reversal of conviction |
E279521
|
entity |
| Predicate | partyRoleOfLopez |
P16985
|
FINISHED |
| Object | criminal 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: criminal defendant | Statement: [Supreme Court affirmed reversal of conviction, partyRoleOfLopez, criminal defendant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partyRoleOfLopez Context triple: [Supreme Court affirmed reversal of conviction, partyRoleOfLopez, criminal defendant]
-
A.
roleInPLO
Indicates that an entity holds or held a specific role or position within the Palestine Liberation Organization (PLO).
-
B.
legalCaseRole
chosen
Indicates the specific role or capacity an entity holds within a legal case, such as plaintiff, defendant, judge, or attorney.
-
C.
roleAtCourt
Indicates the specific position, function, or status an entity holds within a court or courtly setting.
-
D.
namedPersonRole
Indicates that a person is identified by name as holding a specific role or position in a given context.
-
E.
courtRole
Indicates the specific capacity or position an entity holds within a court proceeding or judicial 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_69d6ab01038c819080714901502c84fc |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a50c8d708190ad79ecb57b715d04 |
completed | April 10, 2026, 7:21 a.m. |
| PD | Predicate disambiguation | batch_69d88a829fe481909cc5431de7d6058e |
completed | April 10, 2026, 5:28 a.m. |
Created at: April 8, 2026, 9:41 p.m.