Triple
T17749456
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Curse of the Golden Flower |
E443074
|
entity |
| Predicate | basedOn |
P98
|
FINISHED |
| Object | Thunderstorm |
—
|
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: Thunderstorm | Statement: [Curse of the Golden Flower, basedOn, Thunderstorm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thunderstorm Context triple: [Curse of the Golden Flower, basedOn, Thunderstorm]
-
A.
Thunderstorm
Thunderstorm is a dramatic orchestral depiction of a violent storm, famously portrayed in the fourth movement of Beethoven’s Sixth Symphony, the “Pastoral.”
-
B.
Thunderstorm
chosen
"Thunderstorm" is a landmark 1934 Chinese stage play by dramatist Cao Yu that explores family conflict, social class, and moral decay in Republican-era China.
-
C.
Thunder and Rain
Thunder and Rain is a contemporary Western-themed novel by Charles Martin that blends suspense, romance, and redemption in a modern Texas setting.
-
D.
Lightning
Lightning is the nickname of the Milton Keynes Lightning, a professional ice hockey team based in Milton Keynes, England.
-
E.
Lightning
Lightning is the athletic mascot representing Sage Hill School’s sports teams and school spirit.
- 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48418c0188190beb31809b40e4648 |
completed | April 19, 2026, 7:28 a.m. |
Created at: April 10, 2026, 10:10 a.m.