Triple
T17614507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pietrasanta |
E429047
|
entity |
| Predicate | locatedOnRiver |
P165
|
FINISHED |
| Object | Fiumetto stream |
—
|
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: Fiumetto stream | Statement: [Pietrasanta, locatedOnRiver, Fiumetto stream]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fiumetto stream Context triple: [Pietrasanta, locatedOnRiver, Fiumetto stream]
-
A.
Fiumetta
chosen
Fiumetta is a small watercourse in northern Italy that serves as one of the tributary streams feeding Lake Orta.
-
B.
LINE Webtoon
LINE Webtoon is a popular digital comics platform, originating from South Korea, that publishes a wide range of webtoons and graphic stories optimized for mobile reading.
-
C.
Naver Webtoon
Naver Webtoon is a popular South Korean digital comics platform that hosts and distributes a wide range of webtoons to global audiences.
-
D.
More Fun Comics
More Fun Comics was an early American comic book series from DC Comics that featured a variety of adventure, humor, and superhero stories and helped launch several key characters in the Golden Age of comics.
-
E.
The Comic
The Comic is a notable work by American writer Daniel Fuchs, recognized for its incisive portrayal of show business and character-driven storytelling.
- 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_69d889e1c6148190ba76241e74688f8b |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46d2fd96481908c9f3b566fca6907 |
completed | April 19, 2026, 5:50 a.m. |
Created at: April 10, 2026, 5:51 a.m.