Triple
T12832209
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris of India |
E306815
|
entity |
| Predicate | linkedFeature |
P56313
|
FINISHED |
| Object | historic forts and palaces |
—
|
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: historic forts and palaces | Statement: [Paris of India, linkedFeature, historic forts and palaces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linkedFeature Context triple: [Paris of India, linkedFeature, historic forts and palaces]
-
A.
featureLinked
chosen
Indicates that one feature is associated or connected to another feature in a meaningful or dependent way.
-
B.
linkedSupport
Indicates a relationship where one entity provides support that is directly connected or dependent on another entity’s support or status.
-
C.
linkedLocation
Indicates that one location is associated or connected to another location in a meaningful way, such as being related, referenced, or contextually tied.
-
D.
linkedFigure
Indicates that one figure is associated or connected to another figure, typically as a reference or related visual element.
-
E.
linkedComponent
Indicates that one component is connected or associated with another component in a way that they function or are treated as related parts of a larger whole.
- 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_69d7bdf52b94819096d6f0ba4ab50a98 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9714208f881908f7f8a921362909a |
completed | April 10, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69d96fa08cd481909a946046ba63809f |
completed | April 10, 2026, 9:46 p.m. |
Created at: April 9, 2026, 5:34 p.m.