Triple
T8182391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mack Swain |
E191093
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | Mutual Film |
E68527
|
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: Mutual Film | Statement: [Mack Swain, employer, Mutual Film]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mutual Film Context triple: [Mack Swain, employer, Mutual Film]
-
A.
Mutual Film Corporation
chosen
Mutual Film Corporation was an early 20th-century American film production and distribution company known for producing silent films during the formative years of Hollywood.
-
B.
Minerva Film
Minerva Film is an Italian film distribution and production company known for handling classic and auteur cinema releases.
-
C.
See-Saw Films
See-Saw Films is a British-Australian film and television production company known for acclaimed works such as the Academy Award–winning drama "The King’s Speech."
-
D.
M6 Films
M6 Films is a French film production company known for backing popular international action and thriller movies.
-
E.
Mandeville Films
Mandeville Films is an American film and television production company known for producing a range of commercially successful and critically acclaimed movies and series.
- 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_69ca82c4538081909404325aa5639483 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4c4db8748190aa785e0c70fac497 |
completed | March 31, 2026, 4:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccbf8e8f0c819096f449760ce0d240 |
completed | April 1, 2026, 6:47 a.m. |
Created at: March 30, 2026, 5:40 p.m.