Triple
T1900728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vindolanda |
E37682
|
entity |
| Predicate | writingTabletsMaterial |
P1272
|
FINISHED |
| Object | thin wooden leaf tablets |
—
|
LITERAL 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: thin wooden leaf tablets | Statement: [Vindolanda, writingTabletsMaterial, thin wooden leaf tablets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: writingTabletsMaterial Context triple: [Vindolanda, writingTabletsMaterial, thin wooden leaf tablets]
-
A.
materialUsed
chosen
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
B.
areWrittenOn
Indicates that one entity serves as a surface or medium on which another entity is inscribed, recorded, or written.
-
C.
tabletCount
Indicates the number of tablets associated with or allocated to a given entity or context.
-
D.
writtenIn
Indicates that a work (such as a text, program, or document) is expressed or encoded using a particular language or notation.
-
E.
writingTool
Indicates that one entity serves as a tool or instrument used by another entity for the act of writing.
- F. None of above.
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_69a8861be7148190a680937ec451a304 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb34d94fc8190a5bf1e582c77c725 |
completed | March 7, 2026, 5:10 a.m. |
| PD | Predicate disambiguation | batch_69abafe9f8b0819086d8f6288511c66d |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:35 p.m.