Triple
T5095226
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Édith Piaf |
E114848
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Théo Sarapo
Théo Sarapo was a French singer, actor, and hairdresser best known as Édith Piaf’s much younger second husband and musical partner.
|
E494665
|
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: Théo Sarapo | Statement: [Édith Piaf, spouse, Théo Sarapo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Théo Sarapo Context triple: [Édith Piaf, spouse, Théo Sarapo]
-
A.
Nico Lathouris
Nico Lathouris is an Australian screenwriter and actor best known for co-writing the acclaimed action film "Mad Max: Fury Road" and for his earlier work on the television series "Heartbreak High."
-
B.
Julien BriseBois
Julien BriseBois is a Canadian ice hockey executive best known for building and leading the Tampa Bay Lightning into a modern NHL powerhouse and multiple-time Stanley Cup champion.
-
C.
Théo
Théo is a French given name, typically a short form of Théodore, commonly used for boys in French-speaking countries.
-
D.
Clément
Clément is a French given name, equivalent to Clement in English, commonly used for males.
-
E.
Benoît
Benoît is the French form of the given name Benedict, 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: Théo Sarapo Triple: [Édith Piaf, spouse, Théo Sarapo]
Generated description
Théo Sarapo was a French singer, actor, and hairdresser best known as Édith Piaf’s much younger second husband and musical partner.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Théo Sarapo Target entity description: Théo Sarapo was a French singer, actor, and hairdresser best known as Édith Piaf’s much younger second husband and musical partner.
-
A.
Nico Lathouris
Nico Lathouris is an Australian screenwriter and actor best known for co-writing the acclaimed action film "Mad Max: Fury Road" and for his earlier work on the television series "Heartbreak High."
-
B.
Julien BriseBois
Julien BriseBois is a Canadian ice hockey executive best known for building and leading the Tampa Bay Lightning into a modern NHL powerhouse and multiple-time Stanley Cup champion.
-
C.
Théo
Théo is a French given name, typically a short form of Théodore, commonly used for boys in French-speaking countries.
-
D.
Clément
Clément is a French given name, equivalent to Clement in English, commonly used for males.
-
E.
Benoît
Benoît is the French form of the given name Benedict, 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_69bd443fc49c819089629c00e311310c |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7563ad608190879a26a0bf07c3f6 |
completed | March 20, 2026, 4:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69beba7b87c08190a2581c87f965fa9f |
completed | March 21, 2026, 3:34 p.m. |
| NEDg | Description generation | batch_69bebd1572e08190a69d0d2a35a29fc4 |
completed | March 21, 2026, 3:45 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bebe1069248190a767d0effefed515 |
completed | March 21, 2026, 3:49 p.m. |
Created at: March 20, 2026, 1:40 p.m.