Triple
T23299900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Island President |
E590272
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object |
Actual Films
Actual Films is an independent film production company known for producing socially and politically engaged documentary features.
|
E1581565
|
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: Actual Films | Statement: [The Island President, productionCompany, Actual Films]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Actual Films Context triple: [The Island President, productionCompany, Actual Films]
-
A.
Films 7
Films 7 is a French film production company known for backing movies such as the comedy-thriller "La Totale!".
-
B.
Films 59
Films 59 is a Spanish film production company best known for producing Luis Buñuel’s acclaimed 1961 drama "Viridiana."
-
C.
Flims
Flims is a Swiss alpine resort village in the canton of Graubünden, known for its skiing, hiking, and scenic mountain landscapes.
-
D.
Ten Films
Ten Films is a film production company known for producing the movie "Samba."
-
E.
Home Movies
Home Movies is an animated television sitcom created by Brendon Small and Loren Bouchard that follows a young aspiring filmmaker and his friends as they make amateur films while navigating childhood.
- 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: Actual Films Triple: [The Island President, productionCompany, Actual Films]
Generated description
Actual Films is an independent film production company known for producing socially and politically engaged documentary features.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Actual Films Target entity description: Actual Films is an independent film production company known for producing socially and politically engaged documentary features.
-
A.
Films 7
Films 7 is a French film production company known for backing movies such as the comedy-thriller "La Totale!".
-
B.
Films 59
Films 59 is a Spanish film production company best known for producing Luis Buñuel’s acclaimed 1961 drama "Viridiana."
-
C.
Flims
Flims is a Swiss alpine resort village in the canton of Graubünden, known for its skiing, hiking, and scenic mountain landscapes.
-
D.
Ten Films
Ten Films is a film production company known for producing the movie "Samba."
-
E.
Home Movies
Home Movies is an animated television sitcom created by Brendon Small and Loren Bouchard that follows a young aspiring filmmaker and his friends as they make amateur films while navigating childhood.
- 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_69e25d1c0ecc8190a355aa229f06d0e0 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f196d2b5dc819084b4d0290184de62 |
completed | April 29, 2026, 5:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c4c950f30819090432d04c6abf51d |
completed | May 19, 2026, 11:42 a.m. |
| NEDg | Description generation | batch_6a0c4ef9dcc48190b0c0ca52555f5490 |
completed | May 19, 2026, 11:52 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c506b25ec819084b9522fa827abe7 |
completed | May 19, 2026, 11:58 a.m. |
Created at: April 17, 2026, 5:04 p.m.