Triple
T892102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barra |
E19261
|
entity |
| Predicate | usedBy |
P260
|
FINISHED |
| Object | Mary Barra |
E2752
|
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: Mary Barra | Statement: [Barra, usedBy, Mary Barra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Barra Context triple: [Barra, usedBy, Mary Barra]
-
A.
Mary Barra
chosen
Mary Barra is an American business executive who became the first female CEO of a major global automaker when she took the helm of General Motors.
-
B.
Jim Farley
Jim Farley is an American business executive who serves as the president and chief executive officer of Ford Motor Company.
-
C.
Ursula Burns
Ursula Burns is an American business executive best known for serving as CEO of Xerox, becoming the first Black woman to lead a Fortune 500 company.
-
D.
William Clay Ford Jr.
William Clay Ford Jr. is an American businessman and great-grandson of Henry Ford who has served as executive chairman of Ford Motor Company and is known for promoting sustainability and innovation within the company.
-
E.
Indra Nooyi
Indra Nooyi is an Indian-American business executive best known for serving as the influential former CEO and chairperson of PepsiCo.
- 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_69a4939d37188190848be3d426ebc9ae |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ad0304b081908d4c92bb2beadb81 |
completed | March 1, 2026, 9:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7c025464081908032939637248635 |
completed | March 4, 2026, 5:16 a.m. |
Created at: March 1, 2026, 7:39 p.m.