Triple
T14846386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eassie |
E349101
|
entity |
| Predicate | hasStoneMonument |
P115854
|
FINISHED |
| Object | Pictish cross-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: Pictish cross-slab | Statement: [Eassie, hasStoneMonument, Pictish cross-slab]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStoneMonument Context triple: [Eassie, hasStoneMonument, Pictish cross-slab]
-
A.
hasRomanMonument
Indicates that one entity possesses, contains, or includes a monument of Roman origin or style.
-
B.
hasArchaeologicalMound
Indicates that an entity possesses or contains an archaeological mound, i.e., a raised earthwork or mound of archaeological significance located on or within it.
-
C.
builtMonument
Indicates that one entity constructed or created a monument in honor of, or related to, another entity.
-
D.
hasWorkOnMonument
Indicates that an entity has created, contributed to, or performed work on a particular monument.
-
E.
hasRockReliefSite
Indicates a relationship where a subject is associated with, contains, or is the location of a rock relief site.
- F. None of above. chosen
Provenance (4 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_69d822ec69008190a9232caa68836872 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69ded29236dc8190b7d3a37d09f9fb21 |
completed | April 14, 2026, 11:49 p.m. |
| PD | Predicate disambiguation | batch_69de8c1798c08190b433e9ad21e41a42 |
completed | April 14, 2026, 6:48 p.m. |
| PDg | Predicate description generation | batch_69de8f4b67cc8190b84b59fcec5cf579 |
completed | April 14, 2026, 7:02 p.m. |
Created at: April 10, 2026, 1:53 a.m.