Triple
T19505390
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bright |
E488007
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Bright |
—
|
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: Bright | Statement: [Bright, title, Bright]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bright Context triple: [Bright, title, Bright]
-
A.
Bright
Bright is a notable member of the Philhellenes, a group known for its strong admiration and support for Greek culture and causes.
-
B.
Bright
chosen
Bright is a 2017 urban fantasy action film set in a world where humans coexist with mythical creatures, starring Will Smith and Joel Edgerton and released by Netflix.
-
C.
Bright
Bright is a popular tourist town in northeastern Victoria, Australia, known for its picturesque alpine scenery, autumn foliage, and outdoor recreation activities.
-
D.
Bright
Bright is an English surname borne by various notable figures, including the 19th-century British politician and reformer John Bright.
-
E.
Brighter
"Brighter" is a song by Carole King featured on her album "Music."
- 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_69d8e8d9d1c88190b01cd78b8be49384 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e635113fdc819098ea0f738d01925c |
completed | April 20, 2026, 2:15 p.m. |
Created at: April 10, 2026, 1:40 p.m.