Triple
T20681357
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Poppins franchise |
E508299
|
entity |
| Predicate | notableSong |
P4
|
FINISHED |
| Object | Let’s Go Fly a Kite |
—
|
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: Let’s Go Fly a Kite | Statement: [Mary Poppins franchise, notableSong, Let’s Go Fly a Kite]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Let’s Go Fly a Kite Context triple: [Mary Poppins franchise, notableSong, Let’s Go Fly a Kite]
-
A.
Let’s Go Fly a Kite
chosen
"Let’s Go Fly a Kite" is a cheerful, uplifting song from Disney’s film "Mary Poppins," sung near the end of the movie as the characters celebrate renewed family harmony.
-
B.
Flying a Kite
"Flying a Kite" is a song by the indie rock band Walnut Whales.
-
C.
High as a Kite
"High as a Kite" is a song by American rock band Weezer from their 2019 self-titled "Black Album," noted for its melodic, introspective style.
-
D.
Kite Song
"Kite Song" is a track by Yoko Ono from her expansive 1973 double album "Approximately Infinite Universe," reflecting her experimental and introspective pop-rock style.
-
E.
Yellow Kite
Yellow Kite is a UK-based publishing imprint specializing in health, wellbeing, and personal development titles.
- 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_69e0b4c1164881909a3bf1e3ddb2bc32 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6bea842dc81908106a0c29d1577aa |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 11:45 a.m.