Triple
T19273839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Well Done Abba |
E481994
|
entity |
| Predicate | hasCharacter |
P2308
|
FINISHED |
| Object |
Armaan Ali
Armaan Ali is a fictional character from the Indian film "Well Done Abba."
|
E1367599
|
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: Armaan Ali | Statement: [Well Done Abba, hasCharacter, Armaan Ali]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Armaan Ali Context triple: [Well Done Abba, hasCharacter, Armaan Ali]
-
A.
Hamza Mirza
Hamza Mirza was a Safavid prince of Iran, known primarily as a son of Shah Mohammad Khodabanda during the late 16th century.
-
B.
Ammar Malik
Ammar Malik is an American songwriter known for co-writing major pop hits for artists like Maroon 5 and Gym Class Heroes.
-
C.
Amar Khalil
Amar Khalil is an American R&B singer best known for his work with the influential Oakland-based group Tony! Toni! Toné!.
-
D.
Bilall
Bilall is a Belgian film director and screenwriter best known as one half of the directing duo Adil & Bilall, recognized for stylish action and crime films like "Bad Boys for Life."
-
E.
Rehan Siddiqui
Rehan Siddiqui is a British climbing and mountaineering leader who has served as president of the British Mountaineering Council, the national representative body for climbers, hill walkers, and mountaineers in Britain.
- 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: Armaan Ali Triple: [Well Done Abba, hasCharacter, Armaan Ali]
Generated description
Armaan Ali is a fictional character from the Indian film "Well Done Abba."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Armaan Ali Target entity description: Armaan Ali is a fictional character from the Indian film "Well Done Abba."
-
A.
Hamza Mirza
Hamza Mirza was a Safavid prince of Iran, known primarily as a son of Shah Mohammad Khodabanda during the late 16th century.
-
B.
Ammar Malik
Ammar Malik is an American songwriter known for co-writing major pop hits for artists like Maroon 5 and Gym Class Heroes.
-
C.
Amar Khalil
Amar Khalil is an American R&B singer best known for his work with the influential Oakland-based group Tony! Toni! Toné!.
-
D.
Bilall
Bilall is a Belgian film director and screenwriter best known as one half of the directing duo Adil & Bilall, recognized for stylish action and crime films like "Bad Boys for Life."
-
E.
Rehan Siddiqui
Rehan Siddiqui is a British climbing and mountaineering leader who has served as president of the British Mountaineering Council, the national representative body for climbers, hill walkers, and mountaineers in Britain.
- 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_69d8e8ce54cc8190998418ff1f66ef28 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fbba7758819081c1c78667c59c5e |
completed | April 20, 2026, 10:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a070e748ba48190bc2a17906f7ad842 |
completed | May 15, 2026, 12:15 p.m. |
| NEDg | Description generation | batch_6a070ef513888190b8c9f8c2de36f234 |
completed | May 15, 2026, 12:17 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a070fe766d081909453b1f8563817e8 |
completed | May 15, 2026, 12:21 p.m. |
Created at: April 10, 2026, 1:29 p.m.