Triple
T5778228
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seediq Bale |
E127496
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object |
ARLTA Film
ARLTA Film is a Taiwanese film production company known for producing the acclaimed historical epic "Seediq Bale."
|
E542936
|
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: ARLTA Film | Statement: [Seediq Bale, productionCompany, ARLTA Film]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ARLTA Film Context triple: [Seediq Bale, productionCompany, ARLTA Film]
-
A.
Celluloid
Celluloid is a lightweight, open-source media player for Linux that provides a simple GTK-based interface for the MPV playback engine.
-
B.
BFI
BFI is a University of Chicago research institute that advances economic scholarship and policy through data-driven, market-oriented research.
-
C.
The Film House
The Film House is a film and television production company known for developing and producing screen content such as the project "Newsfront."
-
D.
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."
-
E.
Clerkenwell Films
Clerkenwell Films is a British television and film production company known for creating acclaimed dramas and comedies such as "Misfits" and "Lovesick."
- 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: ARLTA Film Triple: [Seediq Bale, productionCompany, ARLTA Film]
Generated description
ARLTA Film is a Taiwanese film production company known for producing the acclaimed historical epic "Seediq Bale."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: ARLTA Film Target entity description: ARLTA Film is a Taiwanese film production company known for producing the acclaimed historical epic "Seediq Bale."
-
A.
Celluloid
Celluloid is a lightweight, open-source media player for Linux that provides a simple GTK-based interface for the MPV playback engine.
-
B.
BFI
BFI is a University of Chicago research institute that advances economic scholarship and policy through data-driven, market-oriented research.
-
C.
The Film House
The Film House is a film and television production company known for developing and producing screen content such as the project "Newsfront."
-
D.
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."
-
E.
Clerkenwell Films
Clerkenwell Films is a British television and film production company known for creating acclaimed dramas and comedies such as "Misfits" and "Lovesick."
- 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_69c008361fa88190aefa4dc41b051e7f |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c029e107348190a03086f1cbfae0d3 |
completed | March 22, 2026, 5:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c07e6fd260819090d5e3c877c8bd31 |
completed | March 22, 2026, 11:42 p.m. |
| NEDg | Description generation | batch_69c08ba48a1c819090f276116a084a01 |
completed | March 23, 2026, 12:39 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c08c094bd08190bb3d849bf1a80ad0 |
completed | March 23, 2026, 12:40 a.m. |
Created at: March 22, 2026, 3:50 p.m.