Triple
T1973490
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Column of Phocas |
E42852
|
entity |
| Predicate | positionWithinSite |
P3250
|
FINISHED |
| Object | near the eastern end of the Roman Forum |
—
|
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: near the eastern end of the Roman Forum | Statement: [Column of Phocas, positionWithinSite, near the eastern end of the Roman Forum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionWithinSite Context triple: [Column of Phocas, positionWithinSite, near the eastern end of the Roman Forum]
-
A.
positionOn
chosen
Indicates that one entity is located on top of or at a specific place along the surface or extent of another entity.
-
B.
positionEstablishedIn
Indicates the point in time or event when a particular position, role, or office was formally created or instituted.
-
C.
containsSite
Indicates that one entity spatially or structurally includes another entity as a site or location within its bounds.
-
D.
positionInCase
Indicates the specific role, status, or placement that an entity holds within a particular case or legal proceeding.
-
E.
isSiteOf
Indicates that a location or place serves as the setting or host for a particular event, activity, or feature.
- 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_69a8871289048190b00b0d7744b7b2b1 |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb3f477988190b0165fc46b1cccfd |
completed | March 7, 2026, 5:13 a.m. |
| PD | Predicate disambiguation | batch_69abaff7d4a48190ab0d51aefb1c4e31 |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:36 p.m.