Triple
T1927249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrei Tarkovsky |
E40859
|
entity |
| Predicate | awardReceived |
P11
|
FINISHED |
| Object | Golden Lion |
E88544
|
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: Golden Lion | Statement: [Andrei Tarkovsky, awardReceived, Golden Lion]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Golden Lion Context triple: [Andrei Tarkovsky, awardReceived, Golden Lion]
-
A.
Golden Lion
chosen
The Golden Lion is the top prize awarded for the best film at the prestigious Venice Film Festival.
-
B.
Palme d’Or
The Palme d’Or is the highest prize awarded at the Cannes Film Festival, recognizing the best feature film in the festival’s official selection.
-
C.
Silver Bear
The Silver Bear is one of the top prizes awarded at the Berlin International Film Festival, recognizing outstanding achievements in various categories such as acting, directing, and artistic contribution.
-
D.
César statuette
The César statuette is the iconic sculpted trophy presented at France’s premier national film awards, symbolizing excellence in French cinema.
-
E.
Golden Bear
The Golden Bear is the top prize awarded to the best film at the prestigious Berlin International Film Festival, one of the world’s major annual film festivals.
- 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_69a8864711648190b07bed24ed76258e |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb263cdb8819084d0bda98a2a71e0 |
completed | March 7, 2026, 5:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adf3eb5d2c8190b5afd16a822bf0e4 |
completed | March 8, 2026, 10:10 p.m. |
Created at: March 4, 2026, 7:35 p.m.