Triple
T1584981
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liz Imbrie |
E34043
|
entity |
| Predicate | associatedWithCharacter |
P1481
|
FINISHED |
| Object | Tracy Lord |
E35526
|
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: Tracy Lord | Statement: [Liz Imbrie, associatedWithCharacter, Tracy Lord]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tracy Lord Context triple: [Liz Imbrie, associatedWithCharacter, Tracy Lord]
-
A.
Tracy Samantha Lord
chosen
Tracy Samantha Lord is the witty, headstrong Philadelphia socialite at the center of the romantic entanglements in the musical film "High Society."
-
B.
Vivian Lake Brady
Vivian Lake Brady is the daughter of NFL quarterback Tom Brady and supermodel Gisele Bündchen.
-
C.
Daisy Parker
Daisy Parker was the first wife of legendary jazz trumpeter and singer Louis Armstrong, whom he married in the early 1920s.
-
D.
Margo Channing
Margo Channing is a celebrated but aging Broadway star whose career and personal insecurities are central to the drama of the classic film "All About Eve."
-
E.
Edie
Edie is a 2017 British drama film starring Sheila Hancock as an elderly woman who embarks on a life-changing mountain-climbing adventure in the Scottish Highlands.
- 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_69a885fceb2c8190b47e0f7c0aefbff0 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a908f240708190a76bb642fc6a6f42 |
completed | March 5, 2026, 4:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad4698cde88190a113cb7cebc3df1e |
completed | March 8, 2026, 9:51 a.m. |
Created at: March 4, 2026, 7:27 p.m.