Triple
T12691523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iron Pillar of Delhi |
E303214
|
entity |
| Predicate | crossSection |
P73088
|
FINISHED |
| Object | circular |
—
|
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: circular | Statement: [Iron Pillar of Delhi, crossSection, circular]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crossSection Context triple: [Iron Pillar of Delhi, crossSection, circular]
-
A.
crossesSectionOf
Indicates that one entity passes through or over a specific segment or portion of another entity.
-
B.
crossSectionDependsOn
Indicates that the value or behavior of a cross section is determined or influenced by another quantity, condition, or parameter.
-
C.
crossCut
Indicates that one entity intersects or passes through another, typically cutting across it from one side to the other.
-
D.
hasCrossSection
chosen
Indicates that one entity represents or possesses the cross-sectional shape, profile, or slice of another entity.
-
E.
crossType
Indicates a relationship where one entity intersects, passes over, or traverses another, typically implying movement or extension across a boundary, area, or medium.
- 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_69d7bdef90d48190b46b88270e780946 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d962a32c6481908ddaddae4ea267bf |
completed | April 10, 2026, 8:50 p.m. |
| PD | Predicate disambiguation | batch_69d960be63f081908a5ef5ef17a311bf |
completed | April 10, 2026, 8:42 p.m. |
Created at: April 9, 2026, 5:22 p.m.