Triple
T9166478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcia Gay Harden |
E219972
|
entity |
| Predicate | academyAwardFor |
P10689
|
FINISHED |
| Object | Pollock |
E341530
|
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: Pollock | Statement: [Marcia Gay Harden, academyAwardFor, Pollock]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pollock Context triple: [Marcia Gay Harden, academyAwardFor, Pollock]
-
A.
Pollock
chosen
Pollock is a surname of Scottish origin borne by various notable individuals across fields such as art, politics, and academia.
-
B.
Pollack
Pollack is a surname most notably associated with American film director, producer, and actor Sydney Pollack.
-
C.
Fiske
Fiske is the middle name of Harlan F. Stone, who served as Chief Justice of the United States Supreme Court in the mid-20th century.
-
D.
Fisk
Fisk is a surname most famously associated with Carlton Fisk, a Hall of Fame Major League Baseball catcher known for his long career with the Boston Red Sox and Chicago White Sox.
-
E.
Fisher
Fisher is a common English surname borne by numerous notable individuals across fields such as economics, politics, entertainment, and sports.
- 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_69ca83e3633c81908688a9fa2306ba99 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccaade47cc81909b5c127dc8aa1340 |
completed | April 1, 2026, 5:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d05c077f008190ba1bcd82b3fe9a1d |
completed | April 4, 2026, 12:32 a.m. |
Created at: March 30, 2026, 7:22 p.m.