Triple
T9096841
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loretta Brown |
E218045
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Loretta |
E521385
|
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: Loretta | Statement: [Loretta Brown, givenName, Loretta]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Loretta Context triple: [Loretta Brown, givenName, Loretta]
-
A.
Loretta
chosen
Loretta is a feminine given name of Latin origin, often associated with the laurel tree and borne by various notable figures.
-
B.
Loretta Bell
Loretta Bell is a character in Cormac McCarthy's novel "No Country for Old Men," known as the supportive and morally grounded wife of Sheriff Ed Tom Bell.
-
C.
Loretta Rogers
Loretta Rogers is a Canadian philanthropist and longtime director of Rogers Communications, known as the widow of company founder Ted Rogers.
-
D.
Loretta Anne Rogers
Loretta Anne Rogers was a Canadian philanthropist and businesswoman, best known as the widow of telecom magnate Ted Rogers and a longtime director and major shareholder of Rogers Communications.
-
E.
Darlene
Darlene is a fictional character portrayed by actress Dominique Fishback, known from her work in film and television dramas.
- 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_69ca83d9844081908e561e367fda6d45 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc96b7d0d48190a3b15f35bef087e3 |
completed | April 1, 2026, 3:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0181a9ae88190ab80d4e80e919f42 |
completed | April 3, 2026, 7:42 p.m. |
Created at: March 30, 2026, 7:15 p.m.