Triple
T22886797
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vatadage at Polonnaruwa |
E567623
|
entity |
| Predicate | guardstonesDepict |
P85290
|
FINISHED |
| Object | naga (serpent) figures |
—
|
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: naga (serpent) figures | Statement: [Vatadage at Polonnaruwa, guardstonesDepict, naga (serpent) figures]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: guardstonesDepict Context triple: [Vatadage at Polonnaruwa, guardstonesDepict, naga (serpent) figures]
-
A.
monumentDepicts
chosen
Indicates that a monument visually represents, portrays, or is dedicated to a particular person, event, concept, or object.
-
B.
shieldDepicts
Indicates that a shield bears or displays a particular image, symbol, or design as its depiction.
-
C.
hasStoneMonument
Indicates that one entity possesses, contains, or features a stone monument associated with it.
-
D.
castleRepresents
Indicates that a castle stands as a symbol or representation of another entity, concept, or value.
-
E.
oftenDepictedWithInscription
Indicates that the subject is frequently shown or represented together with a written inscription.
- 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_69e2458a92ec81908fc1cd5f6407d2ab |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17fc1e3408190833a062afbea509d |
completed | April 29, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69ef3b6b2e2481908258156937b5a745 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:40 p.m.