Triple
T16649249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rome, Open City |
E404558
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Maria Michi
Maria Michi was an Italian actress best known for her role in Roberto Rossellini’s landmark neorealist film "Rome, Open City."
|
E1226235
|
NE FINISHED |
How this triple was built (4 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: Maria Michi | Statement: [Rome, Open City, starring, Maria Michi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maria Michi Context triple: [Rome, Open City, starring, Maria Michi]
-
A.
Mieko Harada
Mieko Harada is a Japanese actress best known internationally for her intense portrayal of Lady Kaede in Akira Kurosawa’s epic film "Ran."
-
B.
Michiru Ōshima
Michiru Ōshima is a Japanese composer renowned for her orchestral and soundtrack work across anime, film, and video games.
-
C.
Kyoko Ina
Kyoko Ina is a Japanese-American pair skater who became a prominent U.S. national champion and international competitor in the 1990s and early 2000s.
-
D.
Nobuko Imai
Nobuko Imai is a renowned Japanese violist celebrated for her international solo career, chamber music performances, and influential teaching.
-
E.
Miyako Fujitani
Miyako Fujitani is a Japanese aikido instructor and former actress best known as Steven Seagal’s first wife and a key figure in his early martial arts career in Japan.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Maria Michi Triple: [Rome, Open City, starring, Maria Michi]
Generated description
Maria Michi was an Italian actress best known for her role in Roberto Rossellini’s landmark neorealist film "Rome, Open City."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Maria Michi Target entity description: Maria Michi was an Italian actress best known for her role in Roberto Rossellini’s landmark neorealist film "Rome, Open City."
-
A.
Mieko Harada
Mieko Harada is a Japanese actress best known internationally for her intense portrayal of Lady Kaede in Akira Kurosawa’s epic film "Ran."
-
B.
Michiru Ōshima
Michiru Ōshima is a Japanese composer renowned for her orchestral and soundtrack work across anime, film, and video games.
-
C.
Kyoko Ina
Kyoko Ina is a Japanese-American pair skater who became a prominent U.S. national champion and international competitor in the 1990s and early 2000s.
-
D.
Nobuko Imai
Nobuko Imai is a renowned Japanese violist celebrated for her international solo career, chamber music performances, and influential teaching.
-
E.
Miyako Fujitani
Miyako Fujitani is a Japanese aikido instructor and former actress best known as Steven Seagal’s first wife and a key figure in his early martial arts career in Japan.
- F. None of above. chosen
Provenance (5 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_69d8838a41f08190b0c3f79c47df5078 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37ad85ec881909dc6a434a363dab1 |
completed | April 18, 2026, 12:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0084c2a8448190a9f05bc7e1ce7a05 |
completed | May 10, 2026, 1:14 p.m. |
| NEDg | Description generation | batch_6a008607434481909d41e7b8d6f9a4a3 |
completed | May 10, 2026, 1:20 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00868e55dc8190bfc7cd1b78ec4d6d |
completed | May 10, 2026, 1:22 p.m. |
Created at: April 10, 2026, 5:18 a.m.