Triple
T10005074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nathan Followill |
E198220
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Followill |
E198220
|
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: Followill | Statement: [Nathan Followill, familyName, Followill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Followill Context triple: [Nathan Followill, familyName, Followill]
-
A.
Followill
chosen
Followill is a surname most prominently associated with the American rock band Kings of Leon, whose members are part of the Followill family.
-
B.
Windham Falls
Windham Falls is a scenic natural waterfall and popular local getaway spot located near the town of Mirzapur.
-
C.
Litchfield
Litchfield is an English surname historically associated with several notable figures, including members of Charles Darwin’s family.
-
D.
Litchfield
Litchfield is a small unincorporated rural community located in northeastern California.
-
E.
Willingham
Willingham is a surname most notably associated with Tyrone Willingham, an American college football coach.
- 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_69ca830fcca48190bbbd9b20c233835f |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cdcd157d9c8190b863e4264f9a48b1 |
completed | April 2, 2026, 1:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d28209678c8190898d923753bb4472 |
completed | April 5, 2026, 3:38 p.m. |
Created at: March 30, 2026, 8:51 p.m.