Triple
T22449659
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kevin Plank |
E554956
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Plank |
—
|
NE NERFINISHED |
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: Plank | Statement: [Kevin Plank, familyName, Plank]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Plank Context triple: [Kevin Plank, familyName, Plank]
-
A.
Plank
chosen
Plank is a surname most notably associated with Kevin Plank, the American billionaire founder and former CEO of Under Armour.
-
B.
Eisel
Eisel is a surname most notably associated with Austrian former professional road cyclist Bernhard Eisel.
-
C.
Bogo
Bogo is a component city located in the northern part of Cebu province in the Philippines, known as a commercial and transport hub for surrounding municipalities and islands.
-
D.
Bogo
Bogo is an alternative name for the Bilen people, an ethnic group primarily living in Eritrea.
-
E.
Reinholdt
Reinholdt is a masculine given name of Germanic origin, often associated with individuals from German-speaking regions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e5113208190ab58c6b595f9d1d0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b4ae8a08190ba6027f036ce62af |
completed | April 29, 2026, 1:13 a.m. |
Created at: April 16, 2026, 8:48 p.m.