Triple
T770
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States of America |
E14
|
entity |
| Predicate | popularSport |
P251
|
FINISHED |
| Object | American football |
—
|
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: American football | Statement: [United States of America, popularSport, American football]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: popularSport Context triple: [United States of America, popularSport, American football]
-
A.
hasAthletics
Indicates that an entity participates in, is associated with, or offers athletics-related activities or programs.
-
B.
activity
Indicates that an entity is engaged in or performing a particular action, behavior, or process.
-
C.
athleticsNickname
Indicates the commonly used nickname or moniker for an entity’s athletics team or sports program.
-
D.
notableFor
Indicates that an entity is especially recognized or distinguished for a particular quality, achievement, characteristic, or role.
-
E.
athleticsConference
Indicates that an athletic team, program, or institution is affiliated with or competes within a specific athletics conference.
- 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_69a22a285828819081a58308fb963df1 |
completed | Feb. 27, 2026, 11:35 p.m. |
| NER | Named-entity recognition | batch_69a23211f05c8190b8deb03a8540d84d |
completed | Feb. 28, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69a230c2c48481908beb1db3cc9768aa |
completed | Feb. 28, 2026, 12:03 a.m. |
| PDg | Predicate description generation | batch_69a23211181c81909c2db8796d2aded4 |
completed | Feb. 28, 2026, 12:08 a.m. |
Created at: Feb. 27, 2026, 11:36 p.m.