Triple
T21509511
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dodo’s Rka monastery |
E530678
|
entity |
| Predicate | ageRanking |
P121982
|
FINISHED |
| Object | one of the oldest parts of the David Gareja complex |
—
|
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: one of the oldest parts of the David Gareja complex | Statement: [Dodo’s Rka monastery, ageRanking, one of the oldest parts of the David Gareja complex]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ageRanking Context triple: [Dodo’s Rka monastery, ageRanking, one of the oldest parts of the David Gareja complex]
-
A.
peakRanking
Indicates the highest position or rank an entity has ever achieved within a specified ranking system or context.
-
B.
globalRanking
Indicates the position or status of an entity relative to all comparable entities worldwide according to some ranking criteria.
-
C.
populationRankAfter
Indicates the relative position of an entity in a population-based ordering that comes after another entity’s population rank.
-
D.
chronRank
chosen
Indicates the relative chronological order or ranking of events or time-related entities with respect to one another.
-
E.
addressesRank
Indicates that one entity directs communication, content, or behavior toward another entity based on that entity’s rank or hierarchical status.
- 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_69e0c45c81f08190a6b8bbb70a45aae7 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea84042481909b43a7a4c5d2336a |
completed | April 23, 2026, 9:46 a.m. |
| PD | Predicate disambiguation | batch_69e631f6e68081908f5ee4ce7413803e |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:25 p.m.