Triple
T17704482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fasting, Feasting |
E441393
|
entity |
| Predicate | majorCharacter |
P12208
|
FINISHED |
| Object | Uma |
—
|
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: Uma | Statement: [Fasting, Feasting, majorCharacter, Uma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Uma Context triple: [Fasting, Feasting, majorCharacter, Uma]
-
A.
Uma
Uma is an Austronesian language spoken primarily in Central Sulawesi, Indonesia.
-
B.
Uma
chosen
Uma is a central antagonist in Disney's "Descendants" franchise, known as the ambitious and strong-willed daughter of Ursula who leads a pirate crew on the Isle of the Lost.
-
C.
Uma
Uma is a Bengali film directed by Srijit Mukherji, inspired by a real-life story of a terminally ill girl whose father recreates the Durga Puja festival early so she can experience it.
-
D.
Mirina
Mirina is a coastal town on the Greek island of Lemnos, serving as its capital and main port in the northern Aegean Sea.
-
E.
Onami
Onami was an Imperial Japanese Navy destroyer that served in World War II, notably participating in late-war Pacific naval engagements.
- 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_69d8b9ea20b48190ace88bb46b01e6a9 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e47296770c8190b6b172fb647da564 |
completed | April 19, 2026, 6:13 a.m. |
Created at: April 10, 2026, 10:05 a.m.