Triple
T7158182
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George D. and Margo Behrakis Wing |
E166869
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object |
Margo Behrakis
Margo Behrakis is a philanthropist and arts patron known for her significant support of cultural and educational institutions.
|
E645416
|
NE FINISHED |
How this triple was built (4 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: Margo Behrakis | Statement: [George D. and Margo Behrakis Wing, namedAfter, Margo Behrakis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Margo Behrakis Context triple: [George D. and Margo Behrakis Wing, namedAfter, Margo Behrakis]
-
A.
Felicia Minei Behr
Felicia Minei Behr is an American television producer best known for her influential work in daytime soap operas.
-
B.
Stella Sampas
Stella Sampas was the third wife and widow of Beat Generation writer Jack Kerouac, known for managing his literary estate after his death.
-
C.
Eniko Parrish
Eniko Parrish is an American model and media personality best known as the wife of comedian and actor Kevin Hart.
-
D.
Margo Anderson
Margo Anderson is best known as a former wife of American country music star Kenny Rogers.
-
E.
Margo Wilson
Margo Wilson was a pioneering Canadian evolutionary psychologist best known for her influential research on violence, homicide, and parental investment, often conducted in collaboration with Martin Daly.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Margo Behrakis Triple: [George D. and Margo Behrakis Wing, namedAfter, Margo Behrakis]
Generated description
Margo Behrakis is a philanthropist and arts patron known for her significant support of cultural and educational institutions.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Margo Behrakis Target entity description: Margo Behrakis is a philanthropist and arts patron known for her significant support of cultural and educational institutions.
-
A.
Felicia Minei Behr
Felicia Minei Behr is an American television producer best known for her influential work in daytime soap operas.
-
B.
Stella Sampas
Stella Sampas was the third wife and widow of Beat Generation writer Jack Kerouac, known for managing his literary estate after his death.
-
C.
Eniko Parrish
Eniko Parrish is an American model and media personality best known as the wife of comedian and actor Kevin Hart.
-
D.
Margo Anderson
Margo Anderson is best known as a former wife of American country music star Kenny Rogers.
-
E.
Margo Wilson
Margo Wilson was a pioneering Canadian evolutionary psychologist best known for her influential research on violence, homicide, and parental investment, often conducted in collaboration with Martin Daly.
- F. None of above. chosen
Provenance (5 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_69c68887a5cc8190bec0ea96227164f7 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e8109a64819087e132d6d483c07d |
completed | March 27, 2026, 8:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7adbbe8008190b470cf049ba4be52 |
completed | March 28, 2026, 10:30 a.m. |
| NEDg | Description generation | batch_69c7aeca9b0c8190a9255e9e04689192 |
completed | March 28, 2026, 10:34 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7af3aea348190be03e85322d49879 |
completed | March 28, 2026, 10:36 a.m. |
Created at: March 27, 2026, 2:47 p.m.