Triple
T20657950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taxi 2 |
E507676
|
entity |
| Predicate | followedBy |
P78
|
FINISHED |
| Object | Taxi 3 |
—
|
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: Taxi 3 | Statement: [Taxi 2, followedBy, Taxi 3]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taxi 3 Context triple: [Taxi 2, followedBy, Taxi 3]
-
A.
Taxi 3
chosen
Taxi 3 is a 2003 French action-comedy film in the Taxi franchise, following Marseille’s speed-obsessed taxi driver and a bumbling police inspector as they take on a gang of high-tech bank robbers.
-
B.
Taxi 2
Taxi 2 is a 2000 French action-comedy film and sequel in the Taxi franchise, known for its high-speed car chases and humorous storyline set in Marseille.
-
C.
Taxi 5
Taxi 5 is a 2018 French action-comedy film that continues the high-speed, humor-filled adventures of Marseille taxi drivers in the popular Taxi franchise.
-
D.
Taxi 4
Taxi 4 is a 2007 French action-comedy film in the Taxi franchise, following Marseille taxi driver Daniel and his police friend Émilien as they bungle the transfer of a dangerous criminal.
-
E.
Taxi (2004 film)
Taxi (2004 film) is an American action-comedy movie about a speedy New York City cab driver who teams up with a bumbling cop to catch a gang of bank robbers.
- 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_69e0b4bf58c081908e52a4500e03ff83 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6b2eefd5c8190a71d4be690a6ae0e |
completed | April 20, 2026, 11:12 p.m. |
Created at: April 16, 2026, 11:43 a.m.