Triple
T15346854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arlene Phillips |
E366944
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Arlene |
E1108395
|
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: Arlene | Statement: [Arlene Phillips, givenName, Arlene]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arlene Context triple: [Arlene Phillips, givenName, Arlene]
-
A.
Arlene
chosen
Arlene is a feminine given name of English origin that has been borne by various notable figures in arts, entertainment, and public life.
-
B.
Arlene Violet
Arlene Violet is an American lawyer and former Rhode Island Attorney General, recognized as the first woman elected to that office in the United States.
-
C.
Arlene Miles
Arlene Miles was the first wife of American jazz singer and songwriter Mel Tormé.
-
D.
Arnella
Arnella is a feminine given name, notably borne by Arnella Flynn, the daughter of actor Errol Flynn.
-
E.
Rosalyn
Rosalyn is a feminine given name, often considered a variant of Rosalind or Rose, typically associated with meanings related to "rose" and beauty.
- 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_69d85a1355608190a6673ddb67231d54 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e1749bc8190a8b9cbcb27288a5b |
completed | April 16, 2026, 1:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff01f931408190828d87567cecaceb |
completed | May 9, 2026, 9:44 a.m. |
Created at: April 10, 2026, 3:17 a.m.