Triple
T33916597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coach Jack Reilly |
E869475
|
entity |
| Predicate | treatsPlayers |
P180472
|
FINISHED |
| Object | harshly |
—
|
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: harshly | Statement: [Coach Jack Reilly, treatsPlayers, harshly]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: treatsPlayers Context triple: [Coach Jack Reilly, treatsPlayers, harshly]
-
A.
supportsPlayers
Indicates that an entity provides compatibility or functionality for one or more players to participate or be used.
-
B.
managedPlayers
Indicates that one entity has managerial responsibility or authority over the players represented by the other entity.
-
C.
governsPlayersFrom
Indicates that an entity exercises authority or control over players originating from a specified source or group.
-
D.
payingPlayers
Indicates that one or more entities are making a payment to one or more players, typically as compensation, fees, or rewards.
-
E.
intendedPlayers
Indicates the players for whom something (such as a game, item, or activity) is designed or meant to be used.
- 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_69f3499869bc8190b6c33a81686af226 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f74062b9388190b30546cf700a825c |
completed | May 3, 2026, 12:32 p.m. |
| PD | Predicate disambiguation | batch_69f73c802b848190b61a416b7488bd96 |
completed | May 3, 2026, 12:16 p.m. |
| PDg | Predicate description generation | batch_69f74061c440819080434155c2d60341 |
completed | May 3, 2026, 12:32 p.m. |
Created at: May 1, 2026, 1:48 a.m.