Triple
T21743592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Brother |
E536725
|
entity |
| Predicate | hasNameInCredits |
P36847
|
FINISHED |
| Object | The Brother |
—
|
NE NERFINISHED |
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: The Brother | Statement: [The Brother, hasNameInCredits, The Brother]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Brother Context triple: [The Brother, hasNameInCredits, The Brother]
-
A.
The Brother
chosen
The Brother is a mute, telepathic alien who crash-lands in Harlem and navigates life as an undocumented outsider in the film "The Brother from Another Planet."
-
B.
Brother
"Brother" is a Canadian drama film adapted from David Chariandy’s novel, exploring the lives of two Jamaican-Canadian brothers in Toronto and featuring Aaron Pierre in a prominent role.
-
C.
Brother
"Brother" is a notable song by the American rock band Saosin, recognized for its emotive lyrics and post-hardcore sound.
-
D.
Brother
"Brother" is a work titled by Justin Crowe, likely an artwork or creative piece reflecting his contemporary artistic practice.
-
E.
Brother
Brother is a Japanese multinational electronics and electrical equipment company best known for its printers, sewing machines, and other office and home devices.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c46df5448190b4322127ffc4c690 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f01a74592c8190959af631d72df479 |
completed | April 28, 2026, 2:24 a.m. |
Created at: April 16, 2026, 6:49 p.m.