Triple
T23099041
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ted Bundy |
E575974
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Bundy |
—
|
NE NERFINISHED |
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: Bundy | Statement: [Ted Bundy, familyName, Bundy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bundy Context triple: [Ted Bundy, familyName, Bundy]
-
A.
Bundy
chosen
Bundy is a surname most notably associated with McGeorge Bundy, the influential U.S. National Security Advisor during the Kennedy and Johnson administrations.
-
B.
Birchard
Birchard is a masculine given name most notably borne by Birchard Austin Hayes, the son of U.S. President Rutherford B. Hayes.
-
C.
Burgon
Burgon is an English surname most notably associated with composer Geoffrey Burgon.
-
D.
Bonger
Bonger is a Dutch surname most notably associated with Johanna van Gogh-Bonger, the key figure in preserving and promoting Vincent van Gogh’s artistic legacy.
-
E.
Bundy Bear
Bundy Bear is an Australian beer brand mascot, best known as the laid-back polar bear character featured in Bundaberg Rum advertisements.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245c060b48190a9bd61a47a16db17 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18de71a088190b91918e6c4ea6e97 |
completed | April 29, 2026, 4:49 a.m. |
Created at: April 17, 2026, 3:58 p.m.