Triple
T2668789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moray archaeological site |
E55699
|
entity |
| Predicate | hasTerraceComplex |
P41573
|
FINISHED |
| Object | largest circular depression |
—
|
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: largest circular depression | Statement: [Moray archaeological site, hasTerraceComplex, largest circular depression]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTerraceComplex Context triple: [Moray archaeological site, hasTerraceComplex, largest circular depression]
-
A.
hasTerrace
Indicates that one entity includes, features, or is equipped with a terrace as part of its structure or property.
-
B.
numberOfTerraces
Indicates the total count of terraces associated with a given entity.
-
C.
hasCourtyard
Indicates that one entity includes, features, or is characterized by the presence of a courtyard.
-
D.
isTerracedHouse
Indicates that a dwelling is a terraced house, i.e., one in a continuous row of similar houses sharing side walls with neighboring units.
-
E.
formsTerraceWith
Indicates that one entity combines or aligns with another to create or constitute a terrace-like structure or formation.
- 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_69ab49e54de48190be708cd1cf8be073 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd98bacf48190b5633f1a3ec8f0cf |
completed | March 7, 2026, 7:53 a.m. |
| PD | Predicate disambiguation | batch_69abd8190ad481908f3e14ac84d0940a |
completed | March 7, 2026, 7:47 a.m. |
| PDg | Predicate description generation | batch_69abd8f98c348190a68064c565589459 |
completed | March 7, 2026, 7:51 a.m. |
Created at: March 6, 2026, 9:54 p.m.