Triple
T9063792
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mikhail Kalatozov |
E217192
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object |
Lenfilm
Lenfilm is one of Russia’s oldest and most prominent film studios, based in Saint Petersburg and known for producing many classic Soviet-era movies.
|
E773962
|
NE FINISHED |
How this triple was built (4 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: Lenfilm | Statement: [Mikhail Kalatozov, employer, Lenfilm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lenfilm Context triple: [Mikhail Kalatozov, employer, Lenfilm]
-
A.
Mosfilm
Mosfilm is one of Russia’s largest and oldest film studios, renowned for producing many of the Soviet Union’s most iconic movies.
-
B.
Planfilm
Planfilm is a film distribution company known for handling releases such as Orson Welles' documentary-style film "F for Fake."
-
C.
Teitler Film
Teitler Film is a film production company known for producing feature films such as the family sci-fi adventure "Zathura: A Space Adventure."
-
D.
Vides Cinematografica
Vides Cinematografica was an Italian film production company active in the mid-20th century, known for producing notable Italian and international cinema.
-
E.
Anouchka Films
Anouchka Films is a film production company known for producing works such as Jean-Luc Godard’s 1967 political drama "La Chinoise."
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Lenfilm Triple: [Mikhail Kalatozov, employer, Lenfilm]
Generated description
Lenfilm is one of Russia’s oldest and most prominent film studios, based in Saint Petersburg and known for producing many classic Soviet-era movies.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lenfilm Target entity description: Lenfilm is one of Russia’s oldest and most prominent film studios, based in Saint Petersburg and known for producing many classic Soviet-era movies.
-
A.
Mosfilm
Mosfilm is one of Russia’s largest and oldest film studios, renowned for producing many of the Soviet Union’s most iconic movies.
-
B.
Planfilm
Planfilm is a film distribution company known for handling releases such as Orson Welles' documentary-style film "F for Fake."
-
C.
Teitler Film
Teitler Film is a film production company known for producing feature films such as the family sci-fi adventure "Zathura: A Space Adventure."
-
D.
Vides Cinematografica
Vides Cinematografica was an Italian film production company active in the mid-20th century, known for producing notable Italian and international cinema.
-
E.
Anouchka Films
Anouchka Films is a film production company known for producing works such as Jean-Luc Godard’s 1967 political drama "La Chinoise."
- F. None of above. chosen
Provenance (5 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_69ca83d5a7f48190b16c1e59bd43ede0 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc94b9f28481909e20366b0e3d14aa |
completed | April 1, 2026, 3:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfebf8ecb48190b1802b5b41bc7aec |
completed | April 3, 2026, 4:34 p.m. |
| NEDg | Description generation | batch_69cfecbd94a08190841b9bd528fb51a5 |
completed | April 3, 2026, 4:37 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cfed3da2808190b0dbcae662b07957 |
completed | April 3, 2026, 4:39 p.m. |
Created at: March 30, 2026, 7:11 p.m.