Triple
T17379948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tony Kanal |
E422537
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Erin Lokitz
Erin Lokitz is an American actress and model best known for her work in film and television and for being married to musician Tony Kanal of No Doubt.
|
E1428306
|
NE FINISHED |
How this triple was built (4 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: Erin Lokitz | Statement: [Tony Kanal, spouse, Erin Lokitz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Erin Lokitz Context triple: [Tony Kanal, spouse, Erin Lokitz]
-
A.
Erin Burkett
Erin Burkett is an American music industry executive and co-founder of the influential punk rock record label Fat Wreck Chords.
-
B.
Erin Daniels
Erin Daniels is an American actress best known for her role as Dana Fairbanks on the television drama series "The L Word."
-
C.
Erin Richards
Erin Richards is a Welsh actress and director best known for her role as Barbara Kean in the television series "Gotham."
-
D.
Erin Westerman
Erin Westerman is a film producer known for her work on the romantic comedy "Always Be My Maybe" and other contemporary studio projects.
-
E.
Erin Edeiken
Erin Edeiken is a film and television producer best known for her work on the documentary series "The Inventor: Out for Blood in Silicon Valley."
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Erin Lokitz Triple: [Tony Kanal, spouse, Erin Lokitz]
Generated description
Erin Lokitz is an American actress and model best known for her work in film and television and for being married to musician Tony Kanal of No Doubt.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Erin Lokitz Target entity description: Erin Lokitz is an American actress and model best known for her work in film and television and for being married to musician Tony Kanal of No Doubt.
-
A.
Erin Burkett
Erin Burkett is an American music industry executive and co-founder of the influential punk rock record label Fat Wreck Chords.
-
B.
Erin Daniels
Erin Daniels is an American actress best known for her role as Dana Fairbanks on the television drama series "The L Word."
-
C.
Erin Richards
Erin Richards is a Welsh actress and director best known for her role as Barbara Kean in the television series "Gotham."
-
D.
Erin Westerman
Erin Westerman is a film producer known for her work on the romantic comedy "Always Be My Maybe" and other contemporary studio projects.
-
E.
Erin Edeiken
Erin Edeiken is a film and television producer best known for her work on the documentary series "The Inventor: Out for Blood in Silicon Valley."
- F. None of above. chosen
Provenance (5 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_69d889d6535c81908be333c01deaec4e |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a8559748190844c506f6f9230d4 |
completed | April 19, 2026, 2:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0875fb6c1c819080afe7378dfd090e |
completed | May 16, 2026, 1:49 p.m. |
| NEDg | Description generation | batch_6a0877c797bc8190b065869262798e59 |
completed | May 16, 2026, 1:57 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a087841f0dc81909e6cf27c87faa02e |
completed | May 16, 2026, 1:59 p.m. |
Created at: April 10, 2026, 5:45 a.m.