Triple
T3195631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pittsburgh Steelers vs Cleveland Browns |
E66927
|
entity |
| Predicate | contactLevel |
P3669
|
FINISHED |
| Object | full contact |
—
|
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: full contact | Statement: [Pittsburgh Steelers vs Cleveland Browns, contactLevel, full contact]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: contactLevel Context triple: [Pittsburgh Steelers vs Cleveland Browns, contactLevel, full contact]
-
A.
contactWith
Indicates that two entities are in direct or indirect physical or communicative interaction or touch with each other.
-
B.
technicalContact
Indicates that one entity serves as the primary point of contact for technical issues, support, or maintenance related to another entity.
-
C.
hasContactMethod
Indicates that an entity has a specific way or channel through which it can be contacted.
-
D.
engagementLevel
chosen
Indicates the degree or intensity of involvement, interest, or participation one entity has in relation to another entity, activity, or context.
-
E.
hasContactRole
Indicates that an entity serves in a specific role or capacity as a contact for another entity.
- 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_69ad8588ba18819086a10951c32ecb80 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada7163c6c8190b26b05b66740264d |
completed | March 8, 2026, 4:43 p.m. |
| PD | Predicate disambiguation | batch_69ad9e05e4f48190adbe4366cdba2349 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:07 p.m.