Triple
T379707
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Casablanca |
E8651
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object |
Captain Louis Renault
Captain Louis Renault is the charmingly corrupt yet ultimately principled French police prefect in the classic 1942 film "Casablanca."
|
E48308
|
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: Captain Louis Renault | Statement: [Casablanca, character, Captain Louis Renault]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Captain Louis Renault Context triple: [Casablanca, character, Captain Louis Renault]
-
A.
Hector Lefuel
Hector Lefuel was a 19th-century French architect best known for his major role in completing and expanding the Louvre under Napoleon III, helping define the Second Empire architectural style.
-
B.
Stephen Sauvestre
Stephen Sauvestre was a French architect best known for designing the architectural embellishments and final aesthetic of the Eiffel Tower.
-
C.
Aimable Pélissier
Aimable Pélissier was a 19th-century French marshal and military commander best known for his leadership in key campaigns of the Crimean War.
-
D.
Armand
Armand is the given first name of the French poet and Nobel laureate Sully Prudhomme.
-
E.
Jacques
Jacques is the French form of the given name James, commonly used in French-speaking countries.
- 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: Captain Louis Renault Triple: [Casablanca, character, Captain Louis Renault]
Generated description
Captain Louis Renault is the charmingly corrupt yet ultimately principled French police prefect in the classic 1942 film "Casablanca."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Captain Louis Renault Target entity description: Captain Louis Renault is the charmingly corrupt yet ultimately principled French police prefect in the classic 1942 film "Casablanca."
-
A.
Hector Lefuel
Hector Lefuel was a 19th-century French architect best known for his major role in completing and expanding the Louvre under Napoleon III, helping define the Second Empire architectural style.
-
B.
Stephen Sauvestre
Stephen Sauvestre was a French architect best known for designing the architectural embellishments and final aesthetic of the Eiffel Tower.
-
C.
Aimable Pélissier
Aimable Pélissier was a 19th-century French marshal and military commander best known for his leadership in key campaigns of the Crimean War.
-
D.
Armand
Armand is the given first name of the French poet and Nobel laureate Sully Prudhomme.
-
E.
Jacques
Jacques is the French form of the given name James, commonly used in French-speaking countries.
- 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_69a2e7f47dd08190a4e294ccbbe46cd4 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ec2b07248190979229bad3a741c9 |
completed | Feb. 28, 2026, 1:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a3fafe091881908fdf8ddbb6b8a7e6 |
completed | March 1, 2026, 8:38 a.m. |
| NEDg | Description generation | batch_69a3fba8a31881909a32dca83c07e197 |
completed | March 1, 2026, 8:41 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a3fc96cbd88190b05e70c73cbb45c0 |
completed | March 1, 2026, 8:45 a.m. |
Created at: Feb. 28, 2026, 1:08 p.m.