Triple
T23148999
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Temple of Diana on the Aventine |
E578270
|
entity |
| Predicate | dedicatedTo |
P500
|
FINISHED |
| Object | Diana |
—
|
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: Diana | Statement: [Temple of Diana on the Aventine, dedicatedTo, Diana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Diana Context triple: [Temple of Diana on the Aventine, dedicatedTo, Diana]
-
A.
Diana
chosen
Diana is a feminine given name of Latin origin, famously borne by the Roman goddess of the hunt and by Diana, Princess of Wales.
-
B.
Diana
Diana is a renowned sculpture by Brazilian-Italian modernist artist Victor Brecheret, exemplifying his stylized, classical approach to the human figure.
-
C.
Diana Moon
Diana Moon was a specific underground nuclear test conducted by the United States as part of its Operation Bowline series during the era of Cold War weapons development.
-
D.
Melina
Melina is a key resistance fighter and love interest in the science fiction film "Total Recall," known for aiding the protagonist in his struggle against a corrupt Martian regime.
-
E.
Diana Fairfax
Diana Fairfax is an actress known for her role in the British television drama "The Leaving of Liverpool."
- 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_69e245fb8de081908f0eba7b5fd75bc4 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18ed0b76c8190ac61b949d88e9970 |
completed | April 29, 2026, 4:53 a.m. |
Created at: April 17, 2026, 4:01 p.m.