Triple
T17845584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tomonaga Shinichiro |
E445650
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Tomonaga |
—
|
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: Tomonaga | Statement: [Tomonaga Shinichiro, familyName, Tomonaga]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tomonaga Context triple: [Tomonaga Shinichiro, familyName, Tomonaga]
-
A.
Tomonaga
chosen
Tomonaga is a Japanese surname most notably borne by Sin-Itiro Tomonaga, a Nobel Prize–winning theoretical physicist known for his contributions to quantum electrodynamics.
-
B.
Tomoyuki
Tomoyuki is a Japanese masculine given name borne by various notable figures in fields such as the military, arts, and entertainment.
-
C.
Tomok
Tomok is a traditional Batak Toba village on Samosir Island in Lake Toba, Indonesia, known for its ancient stone tombs, cultural performances, and distinctive wooden houses.
-
D.
Tomitaro
Tomitaro is a Japanese given name commonly used for males.
-
E.
Tatsumi
Tatsumi is a residential and waterfront area in Kōtō Ward, Tokyo, known for its housing complexes, sports facilities, and proximity to Tokyo Bay.
- 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_69d8b9f26f18819089c9e43250bee6ae |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48ffa4c648190a88a4b0733493d91 |
completed | April 19, 2026, 8:19 a.m. |
Created at: April 10, 2026, 10:16 a.m.