Triple
T18351638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Underground |
E439679
|
entity |
| Predicate | originalTitle |
P65
|
FINISHED |
| Object | アンダーグラウンド |
—
|
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: アンダーグラウンド | Statement: [Underground, originalTitle, アンダーグラウンド]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: アンダーグラウンド Context triple: [Underground, originalTitle, アンダーグラウンド]
-
A.
Underground
Underground is a 1941 World War II espionage film in which Karen Verne plays a key role, contributing to her recognition as a German-born actress in Hollywood.
-
B.
Underground
Underground is the rapid transit system serving London and some surrounding areas, commonly known as the London Underground or the Tube.
-
C.
Underground
Underground is a historical drama television series that follows a group of enslaved people in the pre–Civil War American South as they attempt a daring escape via the Underground Railroad.
-
D.
Underground
chosen
Underground is a non-fiction book by Haruki Murakami that explores the 1995 Tokyo subway sarin gas attack through interviews with victims and members of the Aum Shinrikyo cult.
-
E.
Underground
Underground is a dystopian political thriller novel by Australian author Andrew McGahan that explores authoritarianism, surveillance, and resistance in a near-future Australia.
- 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_69d8b918221c8190a9f7b563d64ac677 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e514f83b648190b473cf611851c666 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 10:37 a.m.