Triple
T22091304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Samantha Barks |
E545918
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Barks |
—
|
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: Barks | Statement: [Samantha Barks, familyName, Barks]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Barks Context triple: [Samantha Barks, familyName, Barks]
-
A.
Barks
chosen
Barks is the surname of Samantha Barks, a Manx actress and singer best known for her role as Éponine in the film adaptation of "Les Misérables."
-
B.
Doggies
Doggies is a popular nickname for the Canterbury-Bankstown Bulldogs, a professional rugby league club based in Sydney, Australia.
-
C.
Shakey Dog
"Shakey Dog" is a storytelling-heavy hip-hop track by Ghostface Killah from his acclaimed album *Fishscale*, known for its vivid crime narrative and cinematic detail.
-
D.
Mutts
Mutts is a long-running, gently humorous comic strip by Patrick McDonnell that follows the daily lives and friendship of a dog named Earl and a cat named Mooch.
-
E.
Bonek
Bonek is the passionate and famously fervent supporter group of the Indonesian football club Persebaya Surabaya.
- 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_69e11e36d03c8190a83a1ba802b7231b |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f128e5edf08190a6743955bc872417 |
completed | April 28, 2026, 9:38 p.m. |
Created at: April 16, 2026, 8:29 p.m.