Triple
T2854445
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Song to Song |
E63166
|
entity |
| Predicate | producedBy |
P490
|
FINISHED |
| Object | Sarah Green |
E285439
|
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: Sarah Green | Statement: [Song to Song, producedBy, Sarah Green]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sarah Green Context triple: [Song to Song, producedBy, Sarah Green]
-
A.
Sarah Green
chosen
Sarah Green is an American film producer known for her frequent collaborations with director Terrence Malick on critically acclaimed independent films.
-
B.
Helena Springer Green
Helena Springer Green was the wife of American businessman and philanthropist John J. Raskob, a prominent executive at DuPont and General Motors and a key figure behind the construction of the Empire State Building.
-
C.
Beth Greene
Beth Greene is a gentle yet resilient young survivor and aspiring singer from the television series "The Walking Dead."
-
D.
Lisa Rogers
Lisa Rogers is a member of the Rogers family, known as the daughter of Canadian businessman and media magnate Ted Rogers.
-
E.
Susan Garrett
Susan Garrett is known primarily as the wife of former U.S. Secretary of State and Treasury James A. Baker III.
- 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_69ab4c407c408190857d25e027155ce9 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdf60852c8190b66c8719c63a723e |
completed | March 7, 2026, 8:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b03141ec9c8190b8163fdfc00c1ee3 |
completed | March 10, 2026, 2:57 p.m. |
Created at: March 6, 2026, 10:02 p.m.