Triple
T20932618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gabbeh |
E515505
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object |
Hossein Moharami
Hossein Moharami is an actor known for his role in the Iranian film "Gabbeh."
|
E1525105
|
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: Hossein Moharami | Statement: [Gabbeh, stars, Hossein Moharami]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hossein Moharami Context triple: [Gabbeh, stars, Hossein Moharami]
-
A.
Mozaffar Karimi
Mozaffar Karimi is an actor known for his role in the film "Rendition."
-
B.
Abdolrahman Bagheri
Abdolrahman Bagheri is an Iranian actor best known for his role in Abbas Kiarostami’s acclaimed film "Taste of Cherry."
-
C.
Rahmat Shoureshi
Rahmat Shoureshi is an engineer and academic leader known for co-founding Lattice Semiconductor and serving in senior roles at several universities.
-
D.
Soleiman Mohsen Eskandari
Soleiman Mohsen Eskandari was an Iranian politician and activist best known as a pioneering figure of the country’s leftist movement and a founder of the Tudeh Party of Iran.
-
E.
Mohammad Beheshti
Mohammad Beheshti was an influential Iranian cleric, jurist, and revolutionary leader who played a key role in shaping the Islamic Republic’s political and legal system before his assassination in 1981.
- 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: Hossein Moharami Triple: [Gabbeh, stars, Hossein Moharami]
Generated description
Hossein Moharami is an actor known for his role in the Iranian film "Gabbeh."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Hossein Moharami Target entity description: Hossein Moharami is an actor known for his role in the Iranian film "Gabbeh."
-
A.
Mozaffar Karimi
Mozaffar Karimi is an actor known for his role in the film "Rendition."
-
B.
Abdolrahman Bagheri
Abdolrahman Bagheri is an Iranian actor best known for his role in Abbas Kiarostami’s acclaimed film "Taste of Cherry."
-
C.
Rahmat Shoureshi
Rahmat Shoureshi is an engineer and academic leader known for co-founding Lattice Semiconductor and serving in senior roles at several universities.
-
D.
Soleiman Mohsen Eskandari
Soleiman Mohsen Eskandari was an Iranian politician and activist best known as a pioneering figure of the country’s leftist movement and a founder of the Tudeh Party of Iran.
-
E.
Mohammad Beheshti
Mohammad Beheshti was an influential Iranian cleric, jurist, and revolutionary leader who played a key role in shaping the Islamic Republic’s political and legal system before his assassination in 1981.
- 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_69e0b4fb431c8190b9d40e6a72f0cc87 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6f94e980c819083280a9c35af5930 |
completed | April 21, 2026, 4:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0aae5351f88190943ef5a51c5fc6cb |
completed | May 18, 2026, 6:14 a.m. |
| NEDg | Description generation | batch_6a0aaf211d8481908e7c23e35e920e87 |
completed | May 18, 2026, 6:18 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0ab01b5cd48190bf67942798e4db45 |
completed | May 18, 2026, 6:22 a.m. |
Created at: April 16, 2026, 12:49 p.m.