Triple
T11874821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Forster |
E282498
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Forster |
E785574
|
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: Forster | Statement: [Thomas Forster, familyName, Forster]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Forster Context triple: [Thomas Forster, familyName, Forster]
-
A.
Forster
Forster is a coastal town in New South Wales, Australia, known for its beaches, fishing, and holiday tourism.
-
B.
Forster
chosen
Forster is a German surname borne by numerous notable figures, including scientists, writers, and artists.
-
C.
Anne Forster
Anne Forster was the wife of the Irish philosopher and Anglican bishop George Berkeley, known primarily through her marriage into his prominent intellectual and clerical household.
-
D.
June Forster
June Forster is known as the wife of American actor Robert Forster.
-
E.
Fowles
Fowles is the surname of Sylvia Fowles, an American professional basketball player renowned as one of the most dominant centers in WNBA history.
- 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_69d6ab2945d081908a5851c916cbcfb5 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8be1a22448190bd0722188c14d7bd |
completed | April 10, 2026, 9:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f281cac9a48190b4b0f4c53b41110f |
completed | April 29, 2026, 10:10 p.m. |
Created at: April 8, 2026, 9:44 p.m.