Triple
T21480958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marnie Piper |
E529990
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Piper |
—
|
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: Piper | Statement: [Marnie Piper, familyName, Piper]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Piper Context triple: [Marnie Piper, familyName, Piper]
-
A.
Piper
Piper is a feminine given name best known today through its association with author Piper Kerman and her memoir "Orange Is the New Black."
-
B.
Piper
Piper is a 2016 Pixar animated short film about a young sandpiper overcoming its fear of the ocean, acclaimed for its lifelike animation and emotional storytelling.
-
C.
Piper
Piper is a tough, no-nonsense waitress who becomes the fearless ally of Nicolas Cage’s character in the supernatural action film "Drive Angry."
-
D.
Piper
Piper is a large genus of flowering plants best known for species like black pepper (Piper nigrum), which is widely used as a spice worldwide.
-
E.
Piper
chosen
Piper is an English surname borne by various notable individuals across entertainment, sports, and public life.
- 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea338f988190a3044f8d02a567fe |
completed | April 23, 2026, 9:45 a.m. |
Created at: April 16, 2026, 6:21 p.m.