Triple
T11236592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leos Carax |
E265955
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Holy Motors |
E913240
|
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: Holy Motors | Statement: [Leos Carax, directed, Holy Motors]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Holy Motors Context triple: [Leos Carax, directed, Holy Motors]
-
A.
Holy Motors
chosen
Holy Motors is a 2012 surreal French fantasy-drama film by Leos Carax that follows a mysterious actor-like figure performing a series of bizarre roles across Paris in a single day.
-
B.
Logorama
Logorama is a 2009 French animated short film that satirically depicts a world made entirely of corporate logos and mascots.
-
C.
At Eternity’s Gate
At Eternity’s Gate is a 2018 biographical drama film that portrays the final years of painter Vincent van Gogh, featuring Willem Dafoe in an acclaimed lead performance.
-
D.
Sugar Quills
Sugar Quills are a popular wizarding sweet from the Harry Potter universe, shaped like quill pens that can be sucked on in class without teachers noticing.
-
E.
State of Wonder
State of Wonder is a literary novel by Ann Patchett that follows a pharmacologist’s journey into the Amazon rainforest to investigate a colleague’s mysterious death and a secretive medical research project.
- 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_69d6aac656d48190b275efaa7d6074ee |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e904cf888190826fc964f76b5cb2 |
completed | April 9, 2026, 5:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4cc5bcff08190830d09c9aa0187b2 |
completed | April 19, 2026, 12:36 p.m. |
Created at: April 8, 2026, 9:30 p.m.