Triple
T34391603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | remains of Copia |
E882717
|
entity |
| Predicate | materialRemainsOf |
P180188
|
FINISHED |
| Object | ancient town of Copia |
—
|
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: ancient town of Copia | Statement: [remains of Copia, materialRemainsOf, ancient town of Copia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: materialRemainsOf Context triple: [remains of Copia, materialRemainsOf, ancient town of Copia]
-
A.
materialUsed
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
B.
materialProvidedFor
Indicates that one entity supplies or makes available a material for use, processing, or incorporation by another entity or purpose.
-
C.
materialFound
Indicates that a particular material is present, discovered, or detected in association with a specified entity or location.
-
D.
materialFormedIn
Indicates that a material is created, produced, or formed within a specified process, environment, or context.
-
E.
materialStatus
Indicates the current state or condition of a material, such as its availability, usage, or processing stage.
- F. None of above. chosen
Provenance (4 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_69f349c1304081909331872829e38106 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f73397e5488190a9cdce98a0ac0383 |
completed | May 3, 2026, 11:38 a.m. |
| PD | Predicate disambiguation | batch_69f732f3ad248190b4bcbf589d000f0d |
completed | May 3, 2026, 11:35 a.m. |
| PDg | Predicate description generation | batch_69f733970ab48190888f282712a77d4c |
completed | May 3, 2026, 11:37 a.m. |
Created at: May 1, 2026, 1:59 a.m.