Triple
T38407423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanford Wittels & Heisler |
E901371
|
entity |
| Predicate | areaOfPractice |
P85096
|
FINISHED |
| Object | employment law |
—
|
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: employment law | Statement: [Sanford Wittels & Heisler, areaOfPractice, employment law]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: areaOfPractice Context triple: [Sanford Wittels & Heisler, areaOfPractice, employment law]
-
A.
regionOfPractice
Indicates the geographic area or jurisdiction in which an entity regularly conducts its professional activities or services.
-
B.
periodOfPractice
Indicates the span of time during which an activity, role, or practice is carried out.
-
C.
placeOfPractice
Indicates the location where an individual or organization regularly carries out their professional activities or services.
-
D.
practicedInField
chosen
Indicates that an entity has engaged in practical work, training, or professional activity within a specified field or domain.
-
E.
practiceType
Indicates the specific kind or category of practice associated with an entity or activity.
- 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.