Triple
T21786649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mramorje necropolis at Perućac |
E537853
|
entity |
| Predicate | hasTombstoneShape |
P60591
|
FINISHED |
| Object | slab |
—
|
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: slab | Statement: [Mramorje necropolis at Perućac, hasTombstoneShape, slab]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTombstoneShape Context triple: [Mramorje necropolis at Perućac, hasTombstoneShape, slab]
-
A.
hasFormulaOnTombstone
Indicates that a tombstone bears a specific written formula or inscription on it.
-
B.
hasGraveMarkerShape
chosen
Indicates that one entity (a grave or burial site) has a grave marker whose physical form or outline matches the specified shape.
-
C.
hasTerminalShape
Indicates that one entity possesses or exhibits a particular terminal (end) shape defined by another entity.
-
D.
hasApproximateNumberOfTombs
Indicates that an entity is associated with a tomb count that is approximate rather than exact.
-
E.
hasSilhouetteShape
Indicates that one entity has the overall outline or contour shape specified or characterized by another entity.
- 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_69e0c47198f881908cb0d237266c10e9 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0621b5d6881908b74bc999c94fa3d |
completed | April 28, 2026, 7:30 a.m. |
| PD | Predicate disambiguation | batch_69e6be6299988190a34c98fa76d94700 |
completed | April 21, 2026, 12:01 a.m. |
Created at: April 16, 2026, 6:52 p.m.