Triple
T3621970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A Wedding |
E76746
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object | Valerie Curtin |
E268037
|
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: Valerie Curtin | Statement: [A Wedding, hasCastMember, Valerie Curtin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Valerie Curtin Context triple: [A Wedding, hasCastMember, Valerie Curtin]
-
A.
Valerie Curtin
chosen
Valerie Curtin is an American actress and screenwriter known for her work in film and television, including co-writing the acclaimed legal drama "...And Justice for All."
-
B.
Jennifer Butler
Jennifer Butler was an American costume designer best known for her long-term relationship and marriage to actor Bill Murray.
-
C.
Rachael Yamagata
Rachael Yamagata is an American singer-songwriter and pianist known for her soulful, melancholic indie pop and folk-influenced music.
-
D.
Mitchell Alsup
Mitchell Alsup is a computer engineer best known as one of the founders of Transmeta, a company that developed innovative low-power microprocessor technologies.
-
E.
Heaven Hart
Heaven Hart is the daughter of American comedian and actor Kevin Hart.
- 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_69ad85dae2fc81908d1ceadbc6af0089 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc2bb12cc8190bd67597cf3b66a3a |
completed | March 8, 2026, 6:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4331e75d08190ad1ce3e7ef26454a |
completed | March 13, 2026, 3:54 p.m. |
Created at: March 8, 2026, 3:23 p.m.