Triple
T13541308
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Sanderson |
E323391
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Sarah Sanderson |
E323390
|
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: Sarah Sanderson | Statement: [Mary Sanderson, sibling, Sarah Sanderson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sarah Sanderson Context triple: [Mary Sanderson, sibling, Sarah Sanderson]
-
A.
Sarah Sanderson
chosen
Sarah Sanderson is a flirtatious and ditzy witch from the Sanderson sisters trio in the fantasy-comedy film "Hocus Pocus."
-
B.
Leira
Leira is a river in southeastern Norway that serves as one of the tributaries feeding into the country’s longest river, the Glomma.
-
C.
Gelis Stewart
Gelis Stewart, also known as Egidia Stewart, was a medieval Scottish noblewoman of the Stewart family, noted in historical records for her connections to the early Stewart dynasty.
-
D.
Arianne Martell
Arianne Martell is the ambitious and politically astute heir to Dorne in George R. R. Martin’s A Song of Ice and Fire series.
-
E.
Baelen
Baelen is a small municipality in the province of Liège in eastern Belgium, near the German border.
- 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_69d8076776248190bdf0d4fa1f85a5fc |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbafd8ba10819098faadcc6adf251e |
completed | April 12, 2026, 2:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f76bae316081909e048ead31a9575a |
completed | May 3, 2026, 3:37 p.m. |
Created at: April 9, 2026, 9:45 p.m.