Triple
T20191743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Byleth |
E492992
|
entity |
| Predicate | gameDeveloper |
P35248
|
FINISHED |
| Object | Koei Tecmo |
—
|
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: Koei Tecmo | Statement: [Byleth, gameDeveloper, Koei Tecmo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Koei Tecmo Context triple: [Byleth, gameDeveloper, Koei Tecmo]
-
A.
Koei Tecmo
chosen
Koei Tecmo is a Japanese video game company known for developing and publishing action and role-playing titles, including the Dynasty Warriors series and various licensed collaborations.
-
B.
Nippon Koei
Nippon Koei is a major Japanese engineering consulting firm known for its infrastructure and civil engineering projects worldwide.
-
C.
Capcom
Capcom is a Japanese video game developer and publisher best known for creating major franchises such as Resident Evil, Street Fighter, and Monster Hunter.
-
D.
Konami
Konami is a major Japanese entertainment company best known for developing and publishing popular video game franchises such as Metal Gear, Castlevania, and Silent Hill.
-
E.
Toie
Toie is a given name, often used as a short or informal form of the name Toie Roberts.
- 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_69da6268a034819081cbd9ea5a1c9475 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66ad593f88190a1e534fed38b3cd7 |
completed | April 20, 2026, 6:05 p.m. |
Created at: April 11, 2026, 11:37 p.m.