Triple
T37785740
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UNESCO World Heritage Sites in Georgia |
E941950
|
entity |
| Predicate | hasLatestInscriptionYear |
P75923
|
FINISHED |
| Object | 2021 |
—
|
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: 2021 | Statement: [UNESCO World Heritage Sites in Georgia, hasLatestInscriptionYear, 2021]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLatestInscriptionYear Context triple: [UNESCO World Heritage Sites in Georgia, hasLatestInscriptionYear, 2021]
-
A.
hasFirstCohortYear
Indicates the year in which the first cohort associated with an entity began or was established.
-
B.
lastSittingYear
Indicates the specific year in which an entity most recently held a sitting, session, or term.
-
C.
applicationYear
Indicates the year in which an application was submitted or made.
-
D.
matriculationYear
Indicates the calendar year in which an individual formally enrolled or was admitted into an educational program or institution.
-
E.
hasAssociatedYear
chosen
Indicates that an entity is linked to a specific year that is relevant to it (e.g., creation, occurrence, or reference year).
- 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_69f76ee5cb0c81909a363d1c929156c0 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fffbb5d0188190b6d168de8626ff68 |
completed | May 10, 2026, 3:29 a.m. |
| PD | Predicate disambiguation | batch_69fffa3bc1208190a277961385a4789f |
completed | May 10, 2026, 3:23 a.m. |
Created at: May 3, 2026, 4:19 p.m.