Triple
T1900708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vindolanda |
E37682
|
entity |
| Predicate | firstFortBuilt |
P28167
|
FINISHED |
| Object | c. AD 85–90 |
—
|
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: c. AD 85–90 | Statement: [Vindolanda, firstFortBuilt, c. AD 85–90]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstFortBuilt Context triple: [Vindolanda, firstFortBuilt, c. AD 85–90]
-
A.
earliestRecordedFortification
chosen
Indicates that the subject is the earliest known or first historically recorded example of a particular fortification associated with the object.
-
B.
fortressBuiltUnder
Indicates that one structure or location was constructed directly beneath or within the protective area of a fortress.
-
C.
castleBuiltFor
Indicates that a castle was constructed specifically for the benefit, use, or commission of a particular person, group, or purpose.
-
D.
constructionBeganAsFortressIn
Indicates that the construction of something originally began with the purpose or function of serving as a fortress at a specified time or in a specified place.
-
E.
wasFortifiedBy
Indicates that a place or structure received defensive strengthening or fortification through the actions or resources of a specified agent or entity.
- 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.