Triple
T6006175
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanofi |
E133715
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Total |
E555210
|
NE FINISHED |
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: Total | Statement: [Sanofi, foundedBy, Total]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Total Context triple: [Sanofi, foundedBy, Total]
-
A.
Total
Total is an American R&B girl group best known for their 1990s hits and frequent collaborations with Bad Boy Records artists.
-
B.
Total
chosen
Total is the former name of TotalEnergies, a major French multinational oil and gas company that has expanded into broader energy sectors.
-
C.
Overall
Overall is an English-language surname borne by various individuals, including figures in sports, politics, and other fields.
-
D.
Tally
Tally is a common nickname for Tallahassee, the capital city of the U.S. state of Florida.
-
E.
All Over
"All Over" is a popular Afrobeats love song by Nigerian singer Tiwa Savage that helped solidify her status as a leading figure in contemporary African pop music.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c00872444c8190bfaf1739dcec765c |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04f128354819088971ee398cbda77 |
completed | March 22, 2026, 8:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c10895559081908b9efdd32ecef37f |
completed | March 23, 2026, 9:32 a.m. |
Created at: March 22, 2026, 4:06 p.m.