Triple
T17902747
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael C. Hall |
E447623
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Amy Spanger |
E416726
|
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: Amy Spanger | Statement: [Michael C. Hall, spouse, Amy Spanger]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amy Spanger Context triple: [Michael C. Hall, spouse, Amy Spanger]
-
A.
Amy Spanger
chosen
Amy Spanger is an American actress and singer known for her work in Broadway musicals, television, and film.
-
B.
Amy Stechler
Amy Stechler is an American documentary filmmaker and editor known for her early collaborations with Ken Burns on historical films.
-
C.
Elizabeth Natalie Schram
Elizabeth Natalie Schram, known professionally as Bitty Schram, is an American actress best known for her role as Sharona Fleming on the television series "Monk."
-
D.
Emma Flegenheimer
Emma Flegenheimer was the mother of notorious American mobster Dutch Schultz (born Arthur Flegenheimer).
-
E.
Amy Landecker
Amy Landecker is an American actress best known for her role as Sarah Pfefferman on the television series "Transparent."
- 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_69d8b9f59bd48190a6fc925a855b8bac |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49e99c3188190aead24cd3d48c7a7 |
completed | April 19, 2026, 9:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a03290849b081908186afa86cd74ad1 |
completed | May 12, 2026, 1:20 p.m. |
Created at: April 10, 2026, 10:19 a.m.