Triple
T22008778
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kerli Kõiv |
E543519
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Savages |
—
|
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: Savages | Statement: [Kerli Kõiv, notableWork, Savages]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Savages Context triple: [Kerli Kõiv, notableWork, Savages]
-
A.
Savages
Savages is a 2012 crime thriller film directed by Oliver Stone, based on Don Winslow’s novel, about two marijuana growers whose lives spiral into violence after they clash with a Mexican drug cartel.
-
B.
Savages
"Savages" is a song by Brazilian DJ and producer Bruno Martini, known for its energetic electronic sound and international reach in the dance music scene.
-
C.
Savages
chosen
Savages are a British post-punk band known for their intense, minimalist sound and powerful live performances.
-
D.
Savages (album)
Savages is a hard rock studio album by Canadian band Theory of a Deadman, known for its heavy sound and themes of aggression and survival.
-
E.
The Savages
The Savages is a 1966 Doctor Who serial from the classic series, featuring the First Doctor and his companion Steven Taylor as they uncover a society built on the exploitation of another race.
- 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_69e11e2db934819095556760c7d85e4d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127a2aebc8190951ee0bf9fd8e16d |
completed | April 28, 2026, 9:33 p.m. |
Created at: April 16, 2026, 8:21 p.m.