Triple
T28700519
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NHL forwards |
E729537
|
entity |
| Predicate | keySkills |
P87264
|
FINISHED |
| Object | skating speed |
—
|
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: skating speed | Statement: [NHL forwards, keySkills, skating speed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keySkills Context triple: [NHL forwards, keySkills, skating speed]
-
A.
skillSet
Indicates that an entity possesses or is associated with a particular collection of skills or competencies.
-
B.
skilledIn
chosen
Indicates that an entity possesses ability, expertise, or proficiency in performing or using another entity (such as a task, tool, or domain).
-
C.
notableRecruitingSkill
Indicates that an entity is recognized for having significant or distinguished ability in recruiting others.
-
D.
killsAsPartOfJob
Indicates that one entity kills another as a regular or expected duty within their professional role or occupation.
-
E.
skillsFormat
Indicates how a person's skills are organized, structured, or presented (e.g., as a list, categories, or specific layout).
- 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_69f656b4097c8190b6a99be60bc8b670 |
completed | May 2, 2026, 7:55 p.m. |
| PD | Predicate disambiguation | batch_69f651ac855481908e30c3b345d31356 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 5:42 a.m.