Triple
T19979183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cotton collection of manuscripts |
E493769
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Cotton Vespasian A I |
—
|
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: Cotton Vespasian A I | Statement: [Cotton collection of manuscripts, hasPart, Cotton Vespasian A I]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cotton Vespasian A I Context triple: [Cotton collection of manuscripts, hasPart, Cotton Vespasian A I]
-
A.
Cotton Vespasian A.i
chosen
Cotton Vespasian A.i is a medieval manuscript volume from the Cotton Library collection, notable for preserving important early texts and documents.
-
B.
Vespa
Vespa is an iconic Italian brand of motor scooters known for its distinctive design and widespread popularity in urban transportation.
-
C.
Vespa
Vespa is a genus of large social wasps best known for including the true hornets found across Europe and Asia.
-
D.
Certa Cito
Certa Cito is the Latin motto of the British Army’s Royal Corps of Signals, reflecting their role in providing swift and reliable military communications.
-
E.
Auta
Auta is a small settlement on the island of Mitiaro in the Cook Islands.
- 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65d11d2108190bd1d91fdc834888b |
completed | April 20, 2026, 5:06 p.m. |
Created at: April 11, 2026, 3:27 p.m.