Triple
T38407439
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanford Wittels & Heisler |
E901371
|
entity |
| Predicate | sideRepresented |
P135895
|
FINISHED |
| Object | plaintiffs |
—
|
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: plaintiffs | Statement: [Sanford Wittels & Heisler, sideRepresented, plaintiffs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sideRepresented Context triple: [Sanford Wittels & Heisler, sideRepresented, plaintiffs]
-
A.
sideRepresentingLaw
Indicates that one party in a legal matter is acting in a capacity that represents or advocates for the law or legal authority.
-
B.
party represented
chosen
Indicates that one party acts on behalf of, or serves as the official representative of, another party in a given context or proceeding.
-
C.
representedFor
Indicates that one entity has acted or served as the official representative or proxy on behalf of another entity.
-
D.
soughtToRepresent
Indicates an attempt or intention by one entity to act on behalf of, stand in for, or present the interests of another entity.
-
E.
eraRepresented
Indicates that a subject depicts, symbolizes, or stands for a particular historical or temporal era.
- 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_69f76e61e79c81908b787d83b46ab92b |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcd1499e2c81909bafd84dc4810f45 |
completed | May 7, 2026, 5:52 p.m. |
| PD | Predicate disambiguation | batch_69fcccf024ec819086383ffbb6cfc036 |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:31 p.m.