Triple
T15626029
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pixar theatrical short films |
E375680
|
entity |
| Predicate | notableShortFilm |
P40731
|
FINISHED |
| Object | Partly Cloudy |
E375659
|
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: Partly Cloudy | Statement: [Pixar theatrical short films, notableShortFilm, Partly Cloudy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Partly Cloudy Context triple: [Pixar theatrical short films, notableShortFilm, Partly Cloudy]
-
A.
Partly Cloudy
chosen
Partly Cloudy is a Pixar animated short film that humorously and tenderly explores the relationship between a cloud that creates unusual baby animals and the stork who delivers them.
-
B.
Overcast
Overcast is a popular iOS podcast player app known for its smart features, clean design, and development by Marco Arment.
-
C.
BKN
BKN is the IATA airport code for Balkanabat Airport in Turkmenistan.
-
D.
BKN
BKN is the Indian Railways station code for Bikaner Junction, a major railway station in the city of Bikaner, Rajasthan.
-
E.
BKN
BKN is the National Rail station code for Birkenhead North railway station in Merseyside, England.
- 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_69d85cd035a48190b73d5579ab73969a |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e9e5e248190ae54cda1fde51efb |
completed | April 16, 2026, 2:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff5f415c2c81909e232e1c6531da93 |
completed | May 9, 2026, 4:22 p.m. |
Created at: April 10, 2026, 4:14 a.m.