Triple
T2428909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taree |
E52795
|
entity |
| Predicate | nearbyTown |
P3883
|
FINISHED |
| Object | Forster |
E102824
|
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: [Taree, nearbyTown, Forster]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Forster Context triple: [Taree, nearbyTown, Forster]
-
A.
Forster
chosen
Forster is a coastal town in New South Wales, Australia, known for its beaches, fishing, and holiday tourism.
-
B.
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.
-
C.
Paul Forster
Paul Forster is an entrepreneur best known as a co-founder of the global job search engine Indeed.
-
D.
Faulks
Faulks is the surname of British novelist and journalist Sebastian Faulks, best known for his historical and literary fiction.
-
E.
E. M. Forster
E. M. Forster was an English novelist, essayist, and critic best known for works such as "A Passage to India," "Howards End," and "A Room with a View," which explore class, culture, and human connection.
- 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_69ab4959bcc0819083246f9fb10439e3 |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abc99e1b548190aca9a0ba72a9b0f7 |
completed | March 7, 2026, 6:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aebf6634a48190af82eab6b9750323 |
completed | March 9, 2026, 12:39 p.m. |
Created at: March 6, 2026, 9:43 p.m.