Triple
T37816348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kephaloidion |
E942785
|
entity |
| Predicate | laterCulturalSphere |
P199370
|
FINISHED |
| Object | Roman |
—
|
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: Roman | Statement: [Kephaloidion, laterCulturalSphere, Roman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterCulturalSphere Context triple: [Kephaloidion, laterCulturalSphere, Roman]
-
A.
culturalSphere
Indicates that one entity belongs to, is influenced by, or participates in the cultural domain, tradition, or milieu defined by another entity.
-
B.
earlierCulturalSphere
Indicates that one cultural sphere existed or was influential before another in time.
-
C.
laterCulturalContext
chosen
Indicates that one entity is interpreted, used, or understood within a cultural context that arises after the time or culture of the other entity.
-
D.
culturalLayer
Indicates the relationship in which something belongs to, originates from, or is associated with a particular cultural stratum, tradition, or level within a culture.
-
E.
culturalRegion
Indicates that an entity is located in, associated with, or belongs to a specific cultural region or cultural area.
- 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_69f76ee987588190906506e759be5db3 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a0144c75aec81908bdd9e88f2af737a |
completed | May 11, 2026, 2:53 a.m. |
| PD | Predicate disambiguation | batch_6a014405a2d48190a1d58b0b907ad696 |
completed | May 11, 2026, 2:50 a.m. |
Created at: May 3, 2026, 4:19 p.m.