Triple
T20923335
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robin Scherbatsky |
E515270
|
entity |
| Predicate | friend |
P8712
|
FINISHED |
| Object | Lily Aldrin |
—
|
NE NERFINISHED |
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: Lily Aldrin | Statement: [Robin Scherbatsky, friend, Lily Aldrin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lily Aldrin Context triple: [Robin Scherbatsky, friend, Lily Aldrin]
-
A.
Lily Aldrin
chosen
Lily Aldrin is a quirky, artistic kindergarten teacher and one of the central friends in the sitcom "How I Met Your Mother."
-
B.
Lilly Kane
Lilly Kane is a murdered high school student whose death drives the central mystery in the television series "Veronica Mars."
-
C.
Artemis Cooper
Artemis Cooper is a British biographer and historian known for her works on European history and literary figures, including a acclaimed biography of Patrick Leigh Fermor.
-
D.
Tiana Silliphant
Tiana Silliphant is known as the wife of Oscar-winning American screenwriter Stirling Silliphant.
-
E.
Jennifer Lilly
Jennifer Lilly is a film editor known for her work on the feature film "Robot & Frank."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4fb431c8190b9d40e6a72f0cc87 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6f64f767481909deccd77b50bf4ae |
completed | April 21, 2026, 4 a.m. |
Created at: April 16, 2026, 12:49 p.m.