Triple
T14949992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elisa Ambrogio |
E372765
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Magik Markers |
E73840
|
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: Magik Markers | Statement: [Elisa Ambrogio, notableWork, Magik Markers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Magik Markers Context triple: [Elisa Ambrogio, notableWork, Magik Markers]
-
A.
Magik Markers
chosen
Magik Markers is an American noise rock band known for its abrasive, improvisational sound and association with the underground indie and experimental music scenes.
-
B.
Sharpie
Sharpie is a popular brand of permanent markers and writing instruments known for their bold, quick-drying ink used in homes, schools, and offices.
-
C.
Crayon
Crayon is a Nigerian singer and songwriter signed to Mavin Records, known for his Afropop and Afrobeat-influenced music.
-
D.
Ink
Ink is a short-lived 1996 American sitcom starring Ted Danson and Mary Steenburgen as married newspaper journalists balancing their chaotic work and home lives.
-
E.
Ink
"Ink" is a song featured on the Japanese rock band Ghost Stories' album.
- 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_69d85cca979481908747d2a81eba1cea |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded68fae3c81909873b113bfcaca05 |
completed | April 15, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe7e986dfc8190a5cf363dabe6bdef |
completed | May 9, 2026, 12:23 a.m. |
Created at: April 10, 2026, 2:39 a.m.