Triple
T28700467
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NHL defensemen |
E729536
|
entity |
| Predicate | typicalNumberOnIce |
P3766
|
FINISHED |
| Object | two per team at even strength |
—
|
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: two per team at even strength | Statement: [NHL defensemen, typicalNumberOnIce, two per team at even strength]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalNumberOnIce Context triple: [NHL defensemen, typicalNumberOnIce, two per team at even strength]
-
A.
numberOfIceBlocks
Indicates the quantity of ice blocks associated with a given entity or situation.
-
B.
usesStandardIceRink
Indicates that the activity, event, or entity operates on or is conducted within a regulation-size, standard ice rink.
-
C.
performedOnIceRink
Indicates that an action or event took place on an ice rink as its physical setting or surface.
-
D.
typicalIceThickness
Indicates the usual or characteristic thickness of ice under normal or representative conditions.
-
E.
numberOfPlayersOnIcePerTeam
chosen
Indicates the count of players from a single team who are on the ice at the same time during play.
- 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_69f043e6e9688190b6bdd6e5665498ff |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_6a00d9717a9881908194163d719f14d6 |
completed | May 10, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a00d91db2ec81909ebacfc9f0d11dd8 |
completed | May 10, 2026, 7:14 p.m. |
Created at: April 28, 2026, 5:42 a.m.