Triple
T3622869
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irene |
E76766
|
entity |
| Predicate | variantForm |
P4680
|
FINISHED |
| Object | Irène |
E76766
|
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: Irène | Statement: [Irene, variantForm, Irène]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Irène Context triple: [Irene, variantForm, Irène]
-
A.
Irene
chosen
Irene is a feminine given name of Greek origin meaning "peace," borne by numerous historical, religious, and contemporary figures worldwide.
-
B.
Constance Bonacieux
Constance Bonacieux is a key female character in Alexandre Dumas' novel "The Three Musketeers," known as d'Artagnan's love interest and a confidante of Queen Anne.
-
C.
Marie
Marie is a widely used European given name, especially common in French-speaking countries, derived from the Hebrew name Miryam (Mary).
-
D.
Aurélia Thierrée
Aurélia Thierrée is a French actress and circus performer known for her surreal, dreamlike stage shows that blend physical theatre, mime, and illusion.
-
E.
Lucie Dreyfus
Lucie Dreyfus was the devoted wife of French army officer Alfred Dreyfus, who became a prominent figure for her steadfast support and advocacy during the infamous Dreyfus affair.
- 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_69ad85dae2fc81908d1ceadbc6af0089 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc2bc79008190abe6900adcbda8de |
completed | March 8, 2026, 6:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b43320955c8190910c0f15c80f41f4 |
completed | March 13, 2026, 3:54 p.m. |
Created at: March 8, 2026, 3:23 p.m.