Triple
T20477267
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Onslow Stevens |
E502349
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Isabel La Mal
Isabel La Mal was an American actress known for her character roles in mid-20th-century film and television.
|
E1432550
|
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: Isabel La Mal | Statement: [Onslow Stevens, spouse, Isabel La Mal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Isabel La Mal Context triple: [Onslow Stevens, spouse, Isabel La Mal]
-
A.
Izabel
Izabel is a feminine given name, commonly used in various cultures as a variant of Isabel or Isabella.
-
B.
Izabella
"Izabella" is a rock song by Jimi Hendrix, known for its heavy guitar riffs and association with his late-1960s live performances.
-
C.
Ilse Witch
Ilse Witch is a powerful and feared sorceress who serves as a central antagonist in Terry Brooks's Shannara fantasy series.
-
D.
Contessa
Contessa is a character in Tennessee Williams’ novella and its film adaptation "The Roman Spring of Mrs. Stone," representing the sophisticated, manipulative world of Roman high society.
-
E.
Violante
Violante was a 14th-century Italian noblewoman of the powerful Visconti family of Milan, known for her politically significant marriages into European royalty.
- 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: Isabel La Mal Triple: [Onslow Stevens, spouse, Isabel La Mal]
Generated description
Isabel La Mal was an American actress known for her character roles in mid-20th-century film and television.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Isabel La Mal Target entity description: Isabel La Mal was an American actress known for her character roles in mid-20th-century film and television.
-
A.
Izabel
Izabel is a feminine given name, commonly used in various cultures as a variant of Isabel or Isabella.
-
B.
Izabella
"Izabella" is a rock song by Jimi Hendrix, known for its heavy guitar riffs and association with his late-1960s live performances.
-
C.
Ilse Witch
Ilse Witch is a powerful and feared sorceress who serves as a central antagonist in Terry Brooks's Shannara fantasy series.
-
D.
Contessa
Contessa is a character in Tennessee Williams’ novella and its film adaptation "The Roman Spring of Mrs. Stone," representing the sophisticated, manipulative world of Roman high society.
-
E.
Violante
Violante was a 14th-century Italian noblewoman of the powerful Visconti family of Milan, known for her politically significant marriages into European royalty.
- 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_69e0b4af32848190aea80682b44d5d6e |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69966b9748190a5296d8ab03c07a1 |
completed | April 20, 2026, 9:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a088b2359a88190bd1d74a298e56857 |
completed | May 16, 2026, 3:20 p.m. |
| NEDg | Description generation | batch_6a088c3db5fc8190942a51ecd96e22fa |
completed | May 16, 2026, 3:24 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a088cad8f6c819086c52adc846def8b |
completed | May 16, 2026, 3:26 p.m. |
Created at: April 16, 2026, 11:34 a.m.