Triple
T11170404
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman walls of Astorga |
E264257
|
entity |
| Predicate | inferredConstructionEndCentury |
P83221
|
FINISHED |
| Object | 4th century |
—
|
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: 4th century | Statement: [Roman walls of Astorga, inferredConstructionEndCentury, 4th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inferredConstructionEndCentury Context triple: [Roman walls of Astorga, inferredConstructionEndCentury, 4th century]
-
A.
estimatedConstructionEndCentury
chosen
Indicates the century in which the construction of something is estimated to have been completed.
-
B.
approximateUseEndCentury
Indicates that something’s period of use ended around, but not necessarily exactly in, a specified century.
-
C.
declaredInCentury
Indicates that something (such as an event, work, or concept) was formally declared or proclaimed during a specified century.
-
D.
approximateStartCentury
Indicates the century in which something is estimated or roughly believed to have begun.
-
E.
attestedUntilCentury
Indicates the latest century up to which the existence or use of something is historically documented or evidenced.
- 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_69d6aa9dafac8190bd90d2c74f661aa7 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8952e248190b0751669e8c960b7 |
completed | April 9, 2026, 5:57 p.m. |
| PD | Predicate disambiguation | batch_69d75cf0e6e88190973694abe2990973 |
completed | April 9, 2026, 8:01 a.m. |
Created at: April 8, 2026, 9:29 p.m.