Triple
T17563846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arretium |
E427757
|
entity |
| Predicate | materialUsedInPottery |
P1272
|
FINISHED |
| Object | fine clay |
—
|
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: fine clay | Statement: [Arretium, materialUsedInPottery, fine clay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: materialUsedInPottery Context triple: [Arretium, materialUsedInPottery, fine clay]
-
A.
materialUsed
chosen
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
B.
hasTypeOfPottery
Indicates that an entity is associated with or characterized by a specific type or category of pottery.
-
C.
hasPotteryType
Indicates that an entity is associated with or characterized by a specific type or category of pottery.
-
D.
materialFormedIn
Indicates that a material is created, produced, or formed within a specified process, environment, or context.
-
E.
createdCeramicsIn
Indicates that an entity produced or crafted ceramic works in a particular place or location.
- 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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4592bde448190bf5ed2340440e2b7 |
completed | April 19, 2026, 4:25 a.m. |
| PD | Predicate disambiguation | batch_69e3b4fd7d048190b54ee4c6155612a5 |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:50 a.m.