Triple
T6855492
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Vane, 3rd Marquess of Londonderry |
E158129
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Vane |
E180850
|
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: Vane | Statement: [Charles Vane, 3rd Marquess of Londonderry, familyName, Vane]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vane Context triple: [Charles Vane, 3rd Marquess of Londonderry, familyName, Vane]
-
A.
Vane
chosen
Vane is an English surname historically associated with several notable aristocratic and political families in Britain.
-
B.
Venturi
Venturi is an Italian surname most prominently associated with architect Robert Venturi, a key figure in postmodern architecture.
-
C.
Vahni
Vahni is a Sanskrit epithet of the Vedic fire god Agni, emphasizing his blazing, consuming aspect as sacred fire.
-
D.
Vortex
Vortex is a spinning pendulum thrill ride at Thorpe Park known for its intense swinging and rotating motion.
-
E.
Vortex
Vortex is a stand-up steel roller coaster at the Carowinds amusement park known for its inversions and intense, compact layout.
- 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_69c6882fae988190864cbba788c5ebb4 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d86d5a54819088537ada9f8d1105 |
completed | March 27, 2026, 7:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c72fdda9cc8190b039f892d046d7af |
completed | March 28, 2026, 1:33 a.m. |
Created at: March 27, 2026, 2:20 p.m.