Triple
T20310226
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ryker |
E510217
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Riker |
—
|
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: Riker | Statement: [Ryker, hasVariant, Riker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Riker Context triple: [Ryker, hasVariant, Riker]
-
A.
Riker
chosen
Riker is a surname most prominently associated with the American Riker family, including historical figures in New York such as Abraham Rycken.
-
B.
Will Riker
Will Riker is a charismatic Starfleet officer best known as Captain Jean-Luc Picard’s trusted first officer aboard the USS Enterprise in the Star Trek franchise.
-
C.
Robin Riker
Robin Riker is an American actress known for her work in television sitcoms, dramas, and films since the 1970s.
-
D.
Thomas Riker
Thomas Riker is a Star Trek: The Next Generation character who is a duplicate of William Riker created in a transporter accident and later joins the Maquis.
-
E.
Kelly Riker
Kelly Riker is a pivotal character in John Grisham’s legal thriller "The Rainmaker," portrayed as an abused wife whose struggle for safety and justice becomes central to the story’s emotional and moral stakes.
- 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_69e0b4c7491c8190961113c4283b10b0 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e677436af88190a046c44fa45b68b4 |
completed | April 20, 2026, 6:58 p.m. |
Created at: April 16, 2026, 11:19 a.m.