Triple
T19532450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lilli Schwarzkopf |
E488688
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Schwarzkopf |
—
|
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: Schwarzkopf | Statement: [Lilli Schwarzkopf, familyName, Schwarzkopf]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Schwarzkopf Context triple: [Lilli Schwarzkopf, familyName, Schwarzkopf]
-
A.
Schwarzkopf
chosen
Schwarzkopf is a German surname most prominently associated with U.S. Army General Norman Schwarzkopf Jr., who led coalition forces in the Gulf War.
-
B.
Schwarzkopf
Schwarzkopf is a German hair care and styling brand known for its shampoos, dyes, and professional salon products.
-
C.
Redken
Redken is a professional haircare and hair color brand known for its salon-quality products and innovative, science-driven formulas.
-
D.
Garnier Fructis
Garnier Fructis is a popular hair care brand known for its fruit-based formulas and wide range of shampoos, conditioners, and styling products.
-
E.
Tresemmé
Tresemmé is a popular hair care brand known for its salon-inspired shampoos, conditioners, and styling products widely available in retail stores.
- 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6364091f4819088b27d0ffdf6010d |
completed | April 20, 2026, 2:20 p.m. |
Created at: April 10, 2026, 1:41 p.m.