Triple
T23491574
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ayers-Allen |
E570689
|
entity |
| Predicate | replacedByProfessionalName |
P23044
|
FINISHED |
| Object | Phylicia Rashad |
—
|
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: Phylicia Rashad | Statement: [Ayers-Allen, replacedByProfessionalName, Phylicia Rashad]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: replacedByProfessionalName Context triple: [Ayers-Allen, replacedByProfessionalName, Phylicia Rashad]
-
A.
professionalName
Indicates the formal name or title an entity uses in a professional or occupational context.
-
B.
replacedByAdultNameOf
Indicates that an entity (typically a child or informal name) is superseded or substituted by a corresponding adult or formal name.
-
C.
replacementName
chosen
Indicates that one entity serves as a substitute or successor name for another entity, effectively replacing the original designation.
-
D.
retiredNameReplaced
Indicates that an entity’s retired name has been superseded and replaced by a new official name.
-
E.
changedNameBy
Indicates that one entity altered or updated the name of another entity.
- F. None of above.
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_69e245b0b01481908f636939bedd804c |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a7dc631c819099027e3a1c755a66 |
completed | April 29, 2026, 6:40 a.m. |
| PD | Predicate disambiguation | batch_69f0620ac3608190b36916261ea50f54 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 6:04 p.m.