Triple
T10529948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jane Rosenthal |
E248410
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Craig Hatkoff |
E374273
|
NE FINISHED |
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: Craig Hatkoff | Statement: [Jane Rosenthal, spouse, Craig Hatkoff]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Craig Hatkoff Context triple: [Jane Rosenthal, spouse, Craig Hatkoff]
-
A.
Craig Hatkoff
chosen
Craig Hatkoff is an American real estate investor, philanthropist, and co-founder of the Tribeca Film Festival.
-
B.
Doug Mankoff
Doug Mankoff is a film and television producer known for financing and executive producing a wide range of independent and prestige projects.
-
C.
Craig Storper
Craig Storper is a screenwriter best known for writing the Western film "Open Range," directed by and starring Kevin Costner.
-
D.
Rob Hoffman
Rob Hoffman is a music producer best known for his work in hip-hop and R&B, including collaborations with prominent artists in the genre.
-
E.
Josh Kesselman
Josh Kesselman is a film and television producer best known for his work as an executive producer on projects such as the series "The Great."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d381c5c7448190bec34bee7ec72bac |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d509f7d8ac8190b90c1a7f77b23545 |
completed | April 7, 2026, 1:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e8a6567f14819086134cdf3a13aa9b |
completed | April 22, 2026, 10:43 a.m. |
Created at: April 6, 2026, 12:30 p.m.