Triple
T11543397
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Overwatch animated shorts |
E273725
|
entity |
| Predicate | notableCharacter |
P1481
|
FINISHED |
| Object | Hanzo |
E273720
|
NE 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: Hanzo | Statement: [Overwatch animated shorts, notableCharacter, Hanzo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hanzo Context triple: [Overwatch animated shorts, notableCharacter, Hanzo]
-
A.
Hanzo
chosen
Hanzo is a skilled archer and assassin hero in the game Overwatch, known for his precision, mobility, and powerful bow-based abilities.
-
B.
Kanaya Hanzo
Kanaya Hanzo was a Japanese general who rose to the top of the Imperial Japanese Army’s leadership during the early 20th century.
-
C.
Yamanashi Hanzō
Yamanashi Hanzō was a Japanese military officer and colonial administrator who served as Governor-General of Korea during the period of Japanese rule.
-
D.
Tsuchida Gozen
Tsuchida Gozen was a 16th-century Japanese noblewoman best known as the mother of the powerful warlord Oda Nobunaga during the Sengoku period.
-
E.
Dokuganryū Masamune
Dokuganryū Masamune is a Japanese historical television drama (taiga drama) centered on the life of famed warlord Date Masamune.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6aae4dfa48190a3ab0b19a159a3c5 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d886e1d754819089f3b6be3404fa0b |
completed | April 10, 2026, 5:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef12d90b608190b43fc3aa138aa856 |
completed | April 27, 2026, 7:40 a.m. |
Created at: April 8, 2026, 9:37 p.m.