Triple
T20505415
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Christ III |
E503414
|
entity |
| Predicate | manuscriptShelfmark |
P19913
|
FINISHED |
| Object | MS 3501 |
—
|
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: MS 3501 | Statement: [Christ III, manuscriptShelfmark, MS 3501]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MS 3501 Context triple: [Christ III, manuscriptShelfmark, MS 3501]
-
A.
MS 3501
chosen
MS 3501 is the library catalog designation for the Exeter Book, a major 10th-century manuscript of Old English poetry housed at Exeter Cathedral.
-
B.
MS 603
MS 603 is a state highway in Mississippi that serves as a regional connector route in the Gulf Coast area.
-
C.
MS-2
MS-2 is the abbreviated designation for Mississippi's 2nd congressional district, a U.S. House of Representatives district encompassing much of the Mississippi Delta and parts of Jackson.
-
D.
MS 408
MS 408 is the shelfmark designation for the Voynich Manuscript, a famously undeciphered illustrated codex held at the Beinecke Rare Book & Manuscript Library at Yale University.
-
E.
Mss
Mss is the station code for Maassluis railway station in the Netherlands.
- 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_69e0b4b1e52c8190894281cf7e3283ab |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69dc66f00819083c804535e045545 |
completed | April 20, 2026, 9:42 p.m. |
Created at: April 16, 2026, 11:35 a.m.