Triple
T17186613
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Scott Kelly |
E417124
|
entity |
| Predicate | associatedAct |
P37
|
FINISHED |
| Object | Shrinebuilder |
E417132
|
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: Shrinebuilder | Statement: [Scott Kelly, associatedAct, Shrinebuilder]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shrinebuilder Context triple: [Scott Kelly, associatedAct, Shrinebuilder]
-
A.
Shrinebuilder
chosen
Shrinebuilder is a doom/stoner metal supergroup featuring members of influential bands such as Neurosis, Sleep, and Om.
-
B.
Shrine of Secrets
The Shrine of Secrets is a rotating in-game store in Dead by Daylight where players can purchase teachable perks normally tied to specific characters.
-
C.
The Shrine
The Shrine is a historic Los Angeles entertainment venue best known for hosting major film, music, and awards events.
-
D.
The Shrine
The Shrine is a painting by British artist John William Waterhouse, known for its romantic, Pre-Raphaelite-inspired depiction of a contemplative female figure in a richly detailed setting.
-
E.
The Shrine
"The Shrine" is a dramatic work associated with British actress Monica Dolan, showcasing her talent in intense, character-driven storytelling.
- 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_69d886d5f34c8190b24564dfaa63f3fb |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42d96fc588190ad2177d8bb346373 |
completed | April 19, 2026, 1:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a015fce16688190976d3760898ca5d8 |
completed | May 11, 2026, 4:49 a.m. |
Created at: April 10, 2026, 5:37 a.m.