Triple
T10256644
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erica Abi Wright |
E240485
|
entity |
| Predicate | notableSong |
P4
|
FINISHED |
| Object | Bag Lady |
E144145
|
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: Bag Lady | Statement: [Erica Abi Wright, notableSong, Bag Lady]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bag Lady Context triple: [Erica Abi Wright, notableSong, Bag Lady]
-
A.
Bag Lady
chosen
"Bag Lady" is a neo-soul song by Erykah Badu, known for its mellow groove and empowering message about letting go of emotional baggage.
-
B.
Bag Man
"Bag Man" is a nonfiction political book and podcast by Rachel Maddow that investigates the corruption scandal surrounding U.S. Vice President Spiro Agnew.
-
C.
Madame Ban
Madame Ban is the honorific title commonly used for Yoo Soon-taek, the wife of former United Nations Secretary-General Ban Ki-moon and a prominent South Korean public figure.
-
D.
Mrs. Wiggins
Mrs. Wiggins is a minor resident character from the fictional town of Thneedville in Dr. Seuss’s "The Lorax" universe.
-
E.
Mrs. Wiggins
Mrs. Wiggins is a ditzy, slow-typing secretary character, famously portrayed by Carol Burnett in a recurring comedy sketch on her variety show.
- 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_69d381a7e198819090280d5ab885d59e |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d24d299881909615872e2777bdea |
completed | April 7, 2026, 9:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6f7e153b0819084708b6f7127cdea |
completed | April 9, 2026, 12:50 a.m. |
Created at: April 6, 2026, 11:30 a.m.