Triple
T13432601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Astan Quds Razavi |
E313648
|
entity |
| Predicate | chairman |
P377
|
FINISHED |
| Object |
Ahmad Marvi
Ahmad Marvi is an Iranian cleric and political figure who serves as the head of the powerful religious and economic institution overseeing the Imam Reza shrine in Mashhad.
|
E1040659
|
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: Ahmad Marvi | Statement: [Astan Quds Razavi, chairman, Ahmad Marvi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ahmad Marvi Context triple: [Astan Quds Razavi, chairman, Ahmad Marvi]
-
A.
Hamid Nadimi
Hamid Nadimi is an Iranian designer best known for creating the modern national emblem of Iran.
-
B.
Ahmad Matin-Daftari
Ahmad Matin-Daftari was an Iranian lawyer and politician who briefly served as prime minister under Reza Shah Pahlavi in the early 1940s.
-
C.
Malek Asraf
Malek Asraf was a 14th-century ruler of the Chobanid dynasty in northwestern Iran, known for presiding over the final phase of their short-lived post-Ilkhanid state.
-
D.
Sher Mohammad Karimi
Sher Mohammad Karimi is a senior Afghan military leader who served as Chief of General Staff of the Afghan National Army and played a key role in the country’s post-2001 security forces.
-
E.
Mohammad Azar
Mohammad Azar is a machine learning researcher known for co-authoring the influential Rainbow DQN algorithm in deep reinforcement learning.
- 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: Ahmad Marvi Triple: [Astan Quds Razavi, chairman, Ahmad Marvi]
Generated description
Ahmad Marvi is an Iranian cleric and political figure who serves as the head of the powerful religious and economic institution overseeing the Imam Reza shrine in Mashhad.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ahmad Marvi Target entity description: Ahmad Marvi is an Iranian cleric and political figure who serves as the head of the powerful religious and economic institution overseeing the Imam Reza shrine in Mashhad.
-
A.
Hamid Nadimi
Hamid Nadimi is an Iranian designer best known for creating the modern national emblem of Iran.
-
B.
Ahmad Matin-Daftari
Ahmad Matin-Daftari was an Iranian lawyer and politician who briefly served as prime minister under Reza Shah Pahlavi in the early 1940s.
-
C.
Malek Asraf
Malek Asraf was a 14th-century ruler of the Chobanid dynasty in northwestern Iran, known for presiding over the final phase of their short-lived post-Ilkhanid state.
-
D.
Sher Mohammad Karimi
Sher Mohammad Karimi is a senior Afghan military leader who served as Chief of General Staff of the Afghan National Army and played a key role in the country’s post-2001 security forces.
-
E.
Mohammad Azar
Mohammad Azar is a machine learning researcher known for co-authoring the influential Rainbow DQN algorithm in deep reinforcement learning.
- 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_69d806ad0c44819088833ae1ec9e9690 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaed41a5481908800033303224adb |
completed | April 12, 2026, 2:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7398da07081908c3eca6fc4213930 |
completed | May 3, 2026, 12:03 p.m. |
| NEDg | Description generation | batch_69f73b065818819095d26633fc682546 |
completed | May 3, 2026, 12:09 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f73b8635888190b31035bc72676b9d |
completed | May 3, 2026, 12:11 p.m. |
Created at: April 9, 2026, 9:40 p.m.