Triple
T14585108
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Julie Kavner |
E342294
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Kavner
Kavner is the surname of American actress Julie Kavner, best known as the voice of Marge Simpson on the animated television series "The Simpsons."
|
E1108262
|
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: Kavner | Statement: [Julie Kavner, familyName, Kavner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kavner Context triple: [Julie Kavner, familyName, Kavner]
-
A.
Toten
Toten is a traditional rural district in eastern Norway known for its agriculture and scenic landscape, located within Innlandet county.
-
B.
Kavastu
Kavastu is a small village in eastern Estonia known for its historic cable ferry crossing over the Emajõgi River.
-
C.
Vestre Toten
Vestre Toten is a municipality in Innlandet county, Norway, known for its mix of rural landscapes, small towns, and industrial activity.
-
D.
Kove
Kove is an Austronesian language spoken in coastal communities of New Britain in Papua New Guinea.
-
E.
Gravedona
Gravedona is a picturesque town on the shores of Lake Como in northern Italy, known for its historic churches and scenic lakeside setting.
- 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: Kavner Triple: [Julie Kavner, familyName, Kavner]
Generated description
Kavner is the surname of American actress Julie Kavner, best known as the voice of Marge Simpson on the animated television series "The Simpsons."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kavner Target entity description: Kavner is the surname of American actress Julie Kavner, best known as the voice of Marge Simpson on the animated television series "The Simpsons."
-
A.
Toten
Toten is a traditional rural district in eastern Norway known for its agriculture and scenic landscape, located within Innlandet county.
-
B.
Kavastu
Kavastu is a small village in eastern Estonia known for its historic cable ferry crossing over the Emajõgi River.
-
C.
Vestre Toten
Vestre Toten is a municipality in Innlandet county, Norway, known for its mix of rural landscapes, small towns, and industrial activity.
-
D.
Kove
Kove is an Austronesian language spoken in coastal communities of New Britain in Papua New Guinea.
-
E.
Gravedona
Gravedona is a picturesque town on the shores of Lake Como in northern Italy, known for its historic churches and scenic lakeside setting.
- 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_69d822ddc0f081909cd8163c7de298cd |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb4209b988190ad2a7b2dead8ffed |
completed | April 14, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd94bbe6208190af9cd131c147e321 |
completed | May 8, 2026, 7:46 a.m. |
| NEDg | Description generation | batch_69fd984e0e6c819089d967234c5245ee |
completed | May 8, 2026, 8:01 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fd98cf0bcc81909dac826a32daaf04 |
completed | May 8, 2026, 8:03 a.m. |
Created at: April 10, 2026, 1:24 a.m.