Triple
T28449642
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | She (Charles Aznavour song) |
E716536
|
entity |
| Predicate | hasFrenchVersion |
P91232
|
FINISHED |
| Object | Tous les visages de l'amour |
—
|
NE NERFINISHED |
How this triple was built (2 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: Tous les visages de l'amour | Statement: [She (Charles Aznavour song), hasFrenchVersion, Tous les visages de l'amour]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFrenchVersion Context triple: [She (Charles Aznavour song), hasFrenchVersion, Tous les visages de l'amour]
-
A.
containsFrenchPhrases
Indicates that the subject includes one or more phrases expressed in the French language.
-
B.
isFrancophoneCounterpartOf
chosen
Indicates that one entity serves as the French-speaking or French-language equivalent or counterpart of another entity.
-
C.
hasFrenchSector
Indicates that an entity includes, controls, or is associated with a sector or area designated as French.
-
D.
hasChineseVersion
Indicates that an entity has a corresponding version or representation available in Chinese.
-
E.
hasFrenchWikipediaPage
Indicates that the subject entity has a dedicated article on the French-language version of Wikipedia.
- F. None of above.
Provenance (3 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_69efd6b76f8c8190a7ba908aca280942 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f67f0488bc819089fbd2d2478158d3 |
completed | May 2, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69f67e3ed894819094c067c1ef624951 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 28, 2026, 1:51 a.m.