Triple
T1900750
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vindolanda |
E37682
|
entity |
| Predicate | preservationConditions |
P20106
|
FINISHED |
| Object | anaerobic waterlogged layers |
—
|
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: anaerobic waterlogged layers | Statement: [Vindolanda, preservationConditions, anaerobic waterlogged layers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preservationConditions Context triple: [Vindolanda, preservationConditions, anaerobic waterlogged layers]
-
A.
stateOfPreservation
Indicates the condition or degree to which something has been maintained, conserved, or kept intact over time.
-
B.
preservationMethod
Indicates the technique or process used to maintain, protect, or prolong the condition, quality, or usability of something over time.
-
C.
preservationFactor
Indicates the degree to which something is protected, maintained, or kept intact over time, often moderating how much change, loss, or degradation occurs.
-
D.
preservationEnvironment
chosen
Indicates the specific environmental conditions or setting in which something is kept to ensure its long-term preservation.
-
E.
preservedAt
Indicates that something is kept, maintained, or conserved in a particular place or context.
- 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.