Triple
T25593190
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thunder Stone |
E641576
|
entity |
| Predicate | weightBeforeCarving |
P1575
|
FINISHED |
| Object | over 1500 tonnes |
—
|
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: over 1500 tonnes | Statement: [Thunder Stone, weightBeforeCarving, over 1500 tonnes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: weightBeforeCarving Context triple: [Thunder Stone, weightBeforeCarving, over 1500 tonnes]
-
A.
intendedWeight
Indicates the target or desired weight that an entity is meant or planned to have, rather than its current actual weight.
-
B.
weightAfterRecut
Indicates the resulting weight of an item or material after it has been cut, trimmed, or recut from its original form.
-
C.
weight
chosen
Indicates a relationship where a numerical value quantifies how heavy an entity is, often used to measure or compare mass or load.
-
D.
وزن
Indicates a relationship where one entity has, measures, or is characterized by a certain weight or mass.
-
E.
weightCondition
Indicates that a specified weight-related requirement or constraint holds between entities or values.
- 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_69e75dc60d108190b7e2419e36b0134b |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f96ed2188190b4cb38ecb335b677 |
completed | May 2, 2026, 1:17 p.m. |
| PD | Predicate disambiguation | batch_69f5afec3e94819080d9ba86cf8c866e |
completed | May 2, 2026, 8:03 a.m. |
Created at: April 21, 2026, 4:25 p.m.