Triple
T12738889
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | La Rampa (23rd Street) |
E304436
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Yara cinema |
E61948
|
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: Yara cinema | Statement: [La Rampa (23rd Street), hasLandmark, Yara cinema]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yara cinema Context triple: [La Rampa (23rd Street), hasLandmark, Yara cinema]
-
A.
Yara Cinema
chosen
Yara Cinema is a prominent and historic movie theater in Havana, Cuba, known as a cultural landmark and popular gathering place in the Vedado district.
-
B.
Riama Film
Riama Film is an Italian film production company best known for producing Federico Fellini’s classic 1960 drama "La Dolce Vita."
-
C.
Lea Film
Lea Film was an Italian film production company active during the mid-20th century, known for contributing to genre cinema including giallo and thriller films.
-
D.
Geria Film
Geria Film is a film production company known for producing the movie "Fedora."
-
E.
Yannai
Yannai is another name for Alexander Jannaeus, a Hasmonean king of Judea and high priest who ruled in the early 1st century BCE.
- 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_69d7bdf1426c8190a4402e1c4cdec33a |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9646cfcac81909283dca987755c0e |
completed | April 10, 2026, 8:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f67c8ff57c8190a935b5c9f4bb5aa3 |
completed | May 2, 2026, 10:37 p.m. |
Created at: April 9, 2026, 5:26 p.m.