Triple
T19917520
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phipps family |
E478702
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object | Amy Phipps |
—
|
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: Amy Phipps | Statement: [Phipps family, hasMember, Amy Phipps]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amy Phipps Context triple: [Phipps family, hasMember, Amy Phipps]
-
A.
Amy Phipps
chosen
Amy Phipps was an American heiress and philanthropist from the prominent Phipps family, noted for her social influence and charitable activities in the early 20th century.
-
B.
Diane Phipps
Diane Phipps is an individual notable enough to be specifically recorded as a bearer of the surname Phipps.
-
C.
Mary Phillips
Mary Phillips was the wife of pioneering social reformer and photojournalist Jacob Riis, known primarily through her association with his personal and professional life.
-
D.
Ann Butterfield
Ann Butterfield is a fictional character from the romantic drama film "Endless Love."
-
E.
Julie Phillips
Julie Phillips is an actress known for her role in the 2013 film "A Teacher."
- 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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65995bd60819097cfad003dd29731 |
completed | April 20, 2026, 4:51 p.m. |
Created at: April 10, 2026, 1:53 p.m.