Triple
T20859710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarah Williams |
E513582
|
entity |
| Predicate | hasStepmother |
P14091
|
FINISHED |
| Object | Irene |
—
|
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: Irene | Statement: [Sarah Williams, hasStepmother, Irene]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Irene Context triple: [Sarah Williams, hasStepmother, Irene]
-
A.
Irene
Irene is a feminine given name of Greek origin meaning "peace," borne by numerous historical, religious, and contemporary figures worldwide.
-
B.
Irene
Irene is a small, historically significant village and suburb located just outside Pretoria in South Africa, known for its tranquil, tree-lined streets and dairy farm heritage.
-
C.
Irene
Irene was a prominent Hollywood costume designer renowned for her elegant, sophisticated wardrobe creations in classic films.
-
D.
Isidora
Isidora is a feminine given name of Greek origin, commonly considered the female form of Isidore and meaning "gift of Isis."
-
E.
Irene Angelina
Irene Angelina was a Byzantine princess who became Holy Roman Empress and Queen of Sicily through her marriage to Emperor Philip of Swabia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69e0b4f5b01081909452f654d2fc3f50 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c3aabef4819098f0fd24dcc27dbd |
completed | April 21, 2026, 12:24 a.m. |
Created at: April 16, 2026, 12:44 p.m.