Triple
T18144953
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fawn |
E434363
|
entity |
| Predicate | usedBy |
P260
|
FINISHED |
| Object | Lord Fawn |
—
|
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: Lord Fawn | Statement: [Fawn, usedBy, Lord Fawn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lord Fawn Context triple: [Fawn, usedBy, Lord Fawn]
-
A.
Lord Fawn
chosen
Lord Fawn is a cautious, socially ambitious British nobleman in Anthony Trollope’s novel "The Eustace Diamonds," whose engagement to Lizzie Eustace entangles him in scandal and moral compromise.
-
B.
Triffyn Farfog
Triffyn Farfog was an early medieval Welsh king traditionally associated with ruling Dyfed and featuring in the genealogies of Welsh royalty.
-
C.
Falconer
Falconer is a surname most notably associated with American singer and actress Deborah Falconer.
-
D.
Falconer
Falconer is a 1977 novel by John Cheever that explores themes of imprisonment, identity, and redemption through the story of a man incarcerated in a state prison.
-
E.
Wolf of Badenoch
The Wolf of Badenoch was the fearsome nickname of Alexander Stewart, a notoriously ruthless 14th-century Scottish nobleman infamous for his violent raids and lawlessness in the Highlands.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d8b90aac308190801e2c57d8c5bfe5 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4de32d3f88190bd9f406729716407 |
completed | April 19, 2026, 1:52 p.m. |
Created at: April 10, 2026, 10:29 a.m.