Triple
T5779103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | On My Own |
E127513
|
entity |
| Predicate | basedOnLyricsBy |
P1141
|
FINISHED |
| Object | Jean-Marc Natel |
E632159
|
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: Jean-Marc Natel | Statement: [On My Own, basedOnLyricsBy, Jean-Marc Natel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jean-Marc Natel Context triple: [On My Own, basedOnLyricsBy, Jean-Marc Natel]
-
A.
Jean-Marc Natel
chosen
Jean-Marc Natel was a French lyricist best known for co-writing the original French lyrics that inspired the song "I Dreamed a Dream" from the musical Les Misérables.
-
B.
Jean-Philippe Nault
Jean-Philippe Nault is a French Roman Catholic prelate serving as the bishop of the Diocese of Nice.
-
C.
Stéphane Préfontaine
Stéphane Préfontaine is a Canadian former middle-distance runner best known for serving as one of the final torchbearers who lit the Olympic cauldron at the 1976 Montreal Summer Olympics.
-
D.
Éric Jalton
Éric Jalton is a Guadeloupean politician who serves as the long-time mayor of Les Abymes, one of the largest communes in the French Caribbean.
-
E.
Philippe Martin
Philippe Martin is a French film producer known for his work on acclaimed European cinema.
- 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_69c008361fa88190aefa4dc41b051e7f |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0335f23c081909b35020801e3ef12 |
completed | March 22, 2026, 6:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c787e303108190ab14b67c338b1377 |
completed | March 28, 2026, 7:48 a.m. |
Created at: March 22, 2026, 3:50 p.m.