Triple
T15584145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Louis Székely |
E374574
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Chewed Up |
E374583
|
NE FINISHED |
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: Chewed Up | Statement: [Louis Székely, notableWork, Chewed Up]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Chewed Up Context triple: [Louis Székely, notableWork, Chewed Up]
-
A.
Chewed Up
chosen
Chewed Up is a stand-up comedy special by Louis C.K. known for its dark, candid humor and incisive social commentary.
-
B.
Chop Me Up
"Chop Me Up" is a hip hop- and R&B-influenced track from Justin Timberlake’s album FutureSex/LoveSounds, featuring guest verses by Three 6 Mafia and Timbaland.
-
C.
Swallowed
Swallowed is a 1994 song by the British rock band Bush, known for its grunge-influenced sound and success on alternative rock charts.
-
D.
Butchered Tongue
"Butchered Tongue" is a song by Irish musician Hozier from his album "Unreal Unearth," noted for its themes of language, identity, and cultural loss.
-
E.
Kicked in the Teeth
"Kicked in the Teeth" is a hard-driving rock song by AC/DC, known for its aggressive riffs and raw vocal delivery, featured on their 1978 album *Powerage*.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d85ccd575081908909b71a3f3e3a61 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e47971481909e986dd999354628 |
completed | April 16, 2026, 2:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff4c4f71e48190a15eb0a2138f083f |
completed | May 9, 2026, 3:01 p.m. |
Created at: April 10, 2026, 4:11 a.m.