Triple
T2778308
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Conrad |
E61629
|
entity |
| Predicate | betrothedTo |
P33561
|
FINISHED |
| Object | Isabella |
E64321
|
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: Isabella | Statement: [Conrad, betrothedTo, Isabella]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Isabella Context triple: [Conrad, betrothedTo, Isabella]
-
A.
Isabella
chosen
Isabella is a virtuous and resourceful young noblewoman in Horace Walpole’s Gothic novel "The Castle of Otranto," whose peril and resistance drive much of the story’s suspense and drama.
-
B.
Isabel
Isabel is a feminine given name of Spanish origin, widely used in Spanish- and Portuguese-speaking countries and borne by numerous notable historical and contemporary figures.
-
C.
Katherine
Katherine is a regional town in Australia's Northern Territory, known as a key service and transport hub near Nitmiluk (Katherine Gorge) National Park.
-
D.
Beatrix
Beatrix is the first name of the beloved English author and illustrator Beatrix Potter, famed for creating classic children's tales such as "The Tale of Peter Rabbit."
-
E.
Beatrix
Beatrix is the former Queen of the Netherlands who reigned from 1980 until her abdication in 2013.
- 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_69ab4b7e43c48190997b8fc8fb1663ab |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abdd83c5fc8190936b971d5577d3f9 |
completed | March 7, 2026, 8:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afe8a126f881909c378eca59b570a0 |
completed | March 10, 2026, 9:47 a.m. |
Created at: March 6, 2026, 9:57 p.m.