Triple
T20998469
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susan Lewis |
E517213
|
entity |
| Predicate | hasFriend |
P8712
|
FINISHED |
| Object | Mark Greene |
—
|
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: Mark Greene | Statement: [Susan Lewis, hasFriend, Mark Greene]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Greene Context triple: [Susan Lewis, hasFriend, Mark Greene]
-
A.
Mark Greene
chosen
Mark Greene is a central fictional emergency physician and one of the original main characters on the television series "ER."
-
B.
Jeff Greene
Jeff Greene is a fictional character on the HBO comedy series "Curb Your Enthusiasm," known as Larry David’s affable but often morally flexible manager and best friend.
-
C.
Steven Greener
Steven Greener is an American film and television producer and entertainment executive known for his work on popular TV comedies and for managing high-profile talent.
-
D.
Ryan Greene
Ryan Greene is an American record producer and engineer best known for his work with punk rock and alternative bands.
-
E.
Jeffrey Lynn Green
Jeffrey Lynn Green is an American former professional basketball player and current NBA forward known for his versatility and long career with multiple teams.
- 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_69e0b5006e2881909fc2383f841740cc |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc22ca6081908bf054ddcfea9e19 |
completed | April 21, 2026, 4:25 a.m. |
Created at: April 16, 2026, 1:51 p.m.