Triple
T24572696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gardens of Maecenas |
E608002
|
entity |
| Predicate | partiallyLocatedUnder |
P16474
|
FINISHED |
| Object | modern Via Merulana area in Rome |
—
|
NE NERFINISHED |
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: modern Via Merulana area in Rome | Statement: [Gardens of Maecenas, partiallyLocatedUnder, modern Via Merulana area in Rome]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partiallyLocatedUnder Context triple: [Gardens of Maecenas, partiallyLocatedUnder, modern Via Merulana area in Rome]
-
A.
partlyLocatedNear
Indicates that one entity is situated near another, but only a portion or subset of it lies within that nearby area.
-
B.
partlyLocatedOn
Indicates that one entity is situated such that only a portion of it lies on or within the spatial extent of another entity.
-
C.
partlyCoveredBy
chosen
Indicates that one entity is covered or overlapped by another entity, but only to a partial extent rather than completely.
-
D.
locatedUnder
Indicates that one entity is positioned directly or generally beneath another entity in space.
-
E.
canBePlacedUnder
Indicates that one entity is allowed or able to be positioned beneath another entity in a spatial or structural arrangement.
- 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_69e2c4cdab6c8190aae6e5d3de55c95e |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2a9269360819090c44f4483c3533c |
completed | April 30, 2026, 12:58 a.m. |
| PD | Predicate disambiguation | batch_69f2a6c1f07081908edf0b521767e79b |
completed | April 30, 2026, 12:48 a.m. |
Created at: April 18, 2026, 2:28 a.m.