Triple
T22128957
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | In 3-D |
E546859
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Midnight Star |
—
|
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: Midnight Star | Statement: [In 3-D, hasPart, Midnight Star]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Midnight Star Context triple: [In 3-D, hasPart, Midnight Star]
-
A.
Midnight Star
chosen
Midnight Star is an American R&B and funk band best known for their 1980s electro-funk hits like "No Parking (On the Dance Floor)" and "Freak-A-Zoid."
-
B.
Stardust
Stardust is a fantasy novel by Neil Gaiman that blends fairy-tale romance and adventure in a magical realm bordering Victorian England.
-
C.
Stardust
"Stardust" is a notable work created by Michael Hyman Pashelinsky, recognized as a significant contribution to his artistic output.
-
D.
Stardust
"Stardust" is the musical score composed by Ilan Eshkeri for the 2007 fantasy adventure film of the same name, noted for its sweeping orchestral themes and whimsical tone.
-
E.
Stardust
Stardust was a NASA Discovery Program mission that collected and returned samples from the coma of comet Wild 2 and interstellar dust to Earth for detailed laboratory analysis.
- 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_69e11e39bf348190b541bfa16a7b71e0 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12983acfc81908013f66acb31f198 |
completed | April 28, 2026, 9:41 p.m. |
Created at: April 16, 2026, 8:32 p.m.