Triple
T17742701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grace Green Roosevelt |
E442902
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Green |
—
|
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: Green | Statement: [Grace Green Roosevelt, givenName, Green]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Green Context triple: [Grace Green Roosevelt, givenName, Green]
-
A.
Green
chosen
Green is a common English surname of Anglo-Saxon origin, typically derived from a descriptive nickname related to the color green or someone who lived near a village green.
-
B.
Green
Green is a color commonly used in transit systems to designate specific routes or lines, such as the Green Line E branch streetcar.
-
C.
Green
Green is the informal title used to refer to Weezer’s self-titled 2001 album, distinguished by its green cover art.
-
D.
Green
Green is a song featured on the album "Picture Perfect Morning."
-
E.
Green
"Green" is a renowned lyrical prose essay by Chinese writer Zhu Ziqing, celebrated for its delicate depiction of natural scenery and reflective, poetic style.
- 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e47ace58988190b927ca29af7a8b77 |
completed | April 19, 2026, 6:48 a.m. |
Created at: April 10, 2026, 10:09 a.m.