Triple
T15095639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jørgen Tesman |
E360528
|
entity |
| Predicate | hasRelative |
P367
|
FINISHED |
| Object | Aunt Julle |
E360532
|
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: Aunt Julle | Statement: [Jørgen Tesman, hasRelative, Aunt Julle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aunt Julle Context triple: [Jørgen Tesman, hasRelative, Aunt Julle]
-
A.
Aunt Julle
chosen
Aunt Julle is a kindly, old-fashioned, and self-sacrificing aunt in Henrik Ibsen’s play "Hedda Gabler," known for her devotion to her nephew George Tesman and her contrast to Hedda’s coldness.
-
B.
Aunt Allie
Aunt Allie is a fictional guardian figure who serves as the caretaker of Dinah Mannering.
-
C.
Aunt Louie
Aunt Louie is a key character in the crime drama series "Snowfall," known as Franklin Saint’s tough, business-savvy aunt who helps build and manage his growing drug empire.
-
D.
Aunt Glady
Aunt Glady is a supporting character in the film "Home for the Holidays," known as the quirky, warm-hearted aunt of protagonist Claudia Larson.
-
E.
Aunt Lolly
Aunt Lolly is a candy person from the animated series "Adventure Time," known as one of Princess Bubblegum’s relatives in the Candy Kingdom.
- 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_69d85a035aa88190b52a139d3a1b7b6d |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e005466e9c8190a68e1fbeb8922b1a |
completed | April 15, 2026, 9:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69feae21134c81908939ad6ce46703d8 |
completed | May 9, 2026, 3:46 a.m. |
Created at: April 10, 2026, 3:04 a.m.