Triple
T29777947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Janus |
E755432
|
entity |
| Predicate | predecessorCase |
P184377
|
FINISHED |
| Object | Abood v. Detroit Board of Education |
—
|
NE NERFINISHED |
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: Abood v. Detroit Board of Education | Statement: [Mark Janus, predecessorCase, Abood v. Detroit Board of Education]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predecessorCase Context triple: [Mark Janus, predecessorCase, Abood v. Detroit Board of Education]
-
A.
predecessorControl
Indicates that one entity has control or authority over another entity that precedes it in a sequence, process, or hierarchy.
-
B.
predecessorState
Indicates that one state directly precedes another in a sequence or process.
-
C.
predecessorOperator
Indicates that one operator precedes another in an ordered sequence or process.
-
D.
predecessorResult
Indicates that one entity is the outcome or result produced by a preceding entity in a sequence or process.
-
E.
predecessorFunction
Indicates a function that maps each element to its immediate predecessor in an ordered sequence or structure.
- 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_69f0ef878574819088c867fd1a5c8b86 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f7b0e5744c8190a22c1e1d6fcfa466 |
completed | May 3, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f7ab70d034819080295628497d8582 |
completed | May 3, 2026, 8:09 p.m. |
| PDg | Predicate description generation | batch_69f7b0e3917481908a394680d76743c3 |
completed | May 3, 2026, 8:32 p.m. |
Created at: April 28, 2026, 8:48 p.m.