Triple
T17763887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Rosenbaum |
E443451
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Rosenbaum |
—
|
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: Rosenbaum | Statement: [Michael Rosenbaum, familyName, Rosenbaum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rosenbaum Context triple: [Michael Rosenbaum, familyName, Rosenbaum]
-
A.
Rosenbaum
chosen
Rosenbaum is the original family surname of influential American graphic designer Paul Rand, known for his iconic corporate logo designs.
-
B.
Rosenblum
Rosenblum is a Jewish surname borne by various notable individuals, including Israeli journalist and politician Herzl Rosenblum.
-
C.
Rosenstein
Rosenstein is a surname most notably associated with Justin Rosenstein, the American software programmer and co-founder of Asana.
-
D.
Rosen
Rosen is a common Ashkenazi Jewish surname borne by numerous notable figures in politics, arts, science, and business.
-
E.
Rosenfeld
Rosenfeld is a surname of German and Jewish origin borne by various notable individuals across fields such as science, politics, and the arts.
- 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_69d8b9edf16c8190a59ebd245d378f4f |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e485f9fa188190aef5ffeb0b628632 |
completed | April 19, 2026, 7:36 a.m. |
Created at: April 10, 2026, 10:11 a.m.