Triple
T17431310
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Osidda |
E423875
|
entity |
| Predicate | sharesBorderWith |
P224
|
FINISHED |
| Object | Bitti |
—
|
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: Bitti | Statement: [Osidda, sharesBorderWith, Bitti]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bitti Context triple: [Osidda, sharesBorderWith, Bitti]
-
A.
Bitti
chosen
Bitti is a small town and comune in the Province of Nuoro on the Italian island of Sardinia, known for its traditional Sardinian culture and pastoral heritage.
-
B.
Bitto
Bitto is a renowned Italian alpine cheese from the Valtellina region, prized for its long aging potential and rich, complex flavor.
-
C.
Biltine
Biltine is a town in eastern Chad that serves as an administrative and regional center in the Wadi Fira area.
-
D.
Toinette
Toinette is the sharp-witted, outspoken maid in Molière’s comedy "Le Malade imaginaire," known for her clever schemes and satirical commentary on her hypochondriac master.
-
E.
Beretitenti
Beretitenti is the title used for the head of state and government of the Pacific island nation of Kiribati.
- 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_69d889d88b6081908bada047f5b3ba51 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4490072b48190a39b1ac7bb5eb035 |
completed | April 19, 2026, 3:16 a.m. |
Created at: April 10, 2026, 5:46 a.m.