Triple
T9507966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isolde Wagner |
E229317
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Isolde |
E483263
|
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: Isolde | Statement: [Isolde Wagner, givenName, Isolde]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Isolde Context triple: [Isolde Wagner, givenName, Isolde]
-
A.
Isolde
chosen
Isolde is a legendary Irish princess and tragic heroine best known from the medieval romance and Richard Wagner’s opera about her doomed love affair with Tristan.
-
B.
Igraine
Igraine is a noblewoman of Arthurian legend best known as the wife of Uther Pendragon and the mother of King Arthur.
-
C.
Ledaig
Ledaig is a peated single malt Scotch whisky from the Isle of Mull, known for its smoky maritime character and traditional Highland style.
-
D.
Deirdre
Deirdre is a tragic heroine of Irish Celtic mythology, famed for her great beauty and the sorrowful love story that leads to her and her lovers’ downfall.
-
E.
Melisande
Melisande is a minor DC Comics character known primarily as the deceased mother of Talia al Ghul and former lover of the eco-terrorist Ra's al Ghul.
- 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_69ca847611c48190a28c028644198c75 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9855c5e48190a7d8d39b6d601679 |
completed | April 1, 2026, 10:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d13a2b34948190826b1f58258a4f54 |
completed | April 4, 2026, 4:19 p.m. |
Created at: March 30, 2026, 7:57 p.m.