Triple
T29115510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marty Murray |
E737034
|
entity |
| Predicate | worksInLevel |
P39395
|
FINISHED |
| Object | junior ice hockey |
—
|
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: junior ice hockey | Statement: [Marty Murray, worksInLevel, junior ice hockey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worksInLevel Context triple: [Marty Murray, worksInLevel, junior ice hockey]
-
A.
worksAtLevel
Indicates that an entity performs work or holds a role at a specified hierarchical or organizational level.
-
B.
hasWorkingLevel
Indicates that one entity possesses or is assigned a specific operational or functional level within a defined system or context.
-
C.
playedAtLevel
chosen
Indicates that an entity participated or performed in an activity, event, or game at a specified level of difficulty, competition, or hierarchy.
-
D.
works in
Indicates that one entity performs their job or professional activities within the organization, location, or context represented by another entity.
-
E.
worksTo
Indicates that one entity performs work or exerts effort in order to achieve, support, or contribute to another entity or outcome.
- 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_69f077ed54e08190bb02a744e8121a66 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f6d6a6b04c8190bee4cf9c00665ef7 |
completed | May 3, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69f6d26ceb08819091c71c001e954936 |
completed | May 3, 2026, 4:43 a.m. |
Created at: April 28, 2026, 11:22 a.m.