Triple
T20467145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Umbrella Corporation |
E502080
|
entity |
| Predicate | hasKeyPerson |
P256
|
FINISHED |
| Object | Alexia Ashford |
—
|
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: Alexia Ashford | Statement: [Umbrella Corporation, hasKeyPerson, Alexia Ashford]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alexia Ashford Context triple: [Umbrella Corporation, hasKeyPerson, Alexia Ashford]
-
A.
Alexia Ashford
chosen
Alexia Ashford is a central villain in the Resident Evil series, known as a genetically engineered aristocrat who mutates into a powerful bio-organic weapon.
-
B.
Alexis Fields
Alexis Fields is an American actress known for her roles in television series such as "Moesha," "Sister, Sister," and "Keenan & Kel."
-
C.
Alexandra Wise
Alexandra Wise is known as the spouse of British video game composer David Wise.
-
D.
Alexa Woods
Alexa Woods is a skilled and resourceful guide who becomes the human protagonist caught between the warring alien species in the sci-fi horror film "Alien vs. Predator."
-
E.
Alexa Havins
Alexa Havins is an American actress best known for her work in television, including a starring role in the science fiction series "Torchwood."
- 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_69e0b4ae5f1081908768b0c9a3a0bf38 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6995d9d1c81909ee223a35a0850ba |
completed | April 20, 2026, 9:23 p.m. |
Created at: April 16, 2026, 11:33 a.m.