Triple
T190923
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Omar Sharif |
E3718
|
entity |
| Predicate | portrayed |
P1668
|
FINISHED |
| Object |
Sherif Ali
Sherif Ali is a charismatic Bedouin leader and key supporting character in the epic film "Lawrence of Arabia," portrayed by actor Omar Sharif.
|
E24062
|
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: Sherif Ali | Statement: [Omar Sharif, portrayed, Sherif Ali]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sherif Ali Context triple: [Omar Sharif, portrayed, Sherif Ali]
-
A.
Achmed Abdullah
Achmed Abdullah was a Russian-born American writer and screenwriter known for his exotic adventure tales and contributions to early Hollywood cinema.
-
B.
Tariq Anwar
Tariq Anwar is a British film editor known for his acclaimed work on numerous major films, including the Academy Award–winning drama "The King’s Speech."
-
C.
Abdulfattah Jandali
Abdulfattah Jandali is a Syrian-born immigrant and academic who is best known as the biological father of Apple co-founder Steve Jobs.
-
D.
Ali Hakim
Ali Hakim is a comic Persian peddler and charming rogue suitor in the classic Rodgers and Hammerstein musical "Oklahoma!".
-
E.
Chief Usher
The Chief Usher is the senior official responsible for managing the operations, staff, and day-to-day functioning of the White House residence.
- 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: Sherif Ali Triple: [Omar Sharif, portrayed, Sherif Ali]
Generated description
Sherif Ali is a charismatic Bedouin leader and key supporting character in the epic film "Lawrence of Arabia," portrayed by actor Omar Sharif.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sherif Ali Target entity description: Sherif Ali is a charismatic Bedouin leader and key supporting character in the epic film "Lawrence of Arabia," portrayed by actor Omar Sharif.
-
A.
Achmed Abdullah
Achmed Abdullah was a Russian-born American writer and screenwriter known for his exotic adventure tales and contributions to early Hollywood cinema.
-
B.
Tariq Anwar
Tariq Anwar is a British film editor known for his acclaimed work on numerous major films, including the Academy Award–winning drama "The King’s Speech."
-
C.
Abdulfattah Jandali
Abdulfattah Jandali is a Syrian-born immigrant and academic who is best known as the biological father of Apple co-founder Steve Jobs.
-
D.
Ali Hakim
Ali Hakim is a comic Persian peddler and charming rogue suitor in the classic Rodgers and Hammerstein musical "Oklahoma!".
-
E.
Chief Usher
The Chief Usher is the senior official responsible for managing the operations, staff, and day-to-day functioning of the White House residence.
- 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_69a2548debd48190ae3a06d6e65b53c6 |
completed | Feb. 28, 2026, 2:35 a.m. |
| NER | Named-entity recognition | batch_69a25bc96aa081908ef74c9827c9aa48 |
completed | Feb. 28, 2026, 3:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a305e64a9081908f147299826d5ae9 |
completed | Feb. 28, 2026, 3:12 p.m. |
| NEDg | Description generation | batch_69a30679b0648190975dcfaf4f9846bf |
completed | Feb. 28, 2026, 3:15 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69a306e6ce6c8190a77d42643914b03a |
completed | Feb. 28, 2026, 3:16 p.m. |
Created at: Feb. 28, 2026, 2:41 a.m.