Triple
T9425628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 3rdeyegirl |
E227256
|
entity |
| Predicate | backingVocalsBy |
P9646
|
FINISHED |
| Object | Hannah Welton |
E800509
|
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: Hannah Welton | Statement: [3rdeyegirl, backingVocalsBy, Hannah Welton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hannah Welton Context triple: [3rdeyegirl, backingVocalsBy, Hannah Welton]
-
A.
Hannah Welton
chosen
Hannah Welton is an American drummer best known for performing with Prince as part of his backing band 3rdeyegirl.
-
B.
Hannah Walters
Hannah Walters is a British actress and producer known for her work in film and television and for being married to actor Stephen Graham.
-
C.
Hannah Johnston
Hannah Johnston is the birth name of Hannah Johnston Iredell, a historical figure known primarily in connection with the Iredell family.
-
D.
Hannah Weaver
Hannah Weaver is a young law student who becomes a pivotal love interest and emotional anchor in the romantic comedy film "Crazy, Stupid, Love."
-
E.
Hannah Lindsey
Hannah Lindsey was the wife of English Unitarian minister Theophilus Lindsey and a supportive partner in his religious and reformist endeavors in the 18th century.
- 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_69ca8436ba308190903e470776d2d893 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd7c8f59dc8190854dfc0d287731c6 |
completed | April 1, 2026, 8:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d139d4e660819099ec1ffd6c8d3305 |
completed | April 4, 2026, 4:18 p.m. |
Created at: March 30, 2026, 7:49 p.m.