Triple
T18884797
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vikram Seth |
E461930
|
entity |
| Predicate | hasWritten |
P2831
|
FINISHED |
| Object | Mappings |
—
|
NE NERFINISHED |
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: Mappings | Statement: [Vikram Seth, hasWritten, Mappings]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mappings Context triple: [Vikram Seth, hasWritten, Mappings]
-
A.
Mappings
chosen
Mappings is a poetry collection by Indian author Vikram Seth that showcases his early lyrical and reflective verse.
-
B.
Maps
Maps is Apple's native mapping and navigation application that provides turn-by-turn directions, points of interest, and integrated location services across its devices.
-
C.
MAP
MAP was the abbreviated name used for the United Kingdom’s Ministry of Aircraft Production, the World War II government department responsible for overseeing and increasing aircraft manufacturing.
-
D.
MAP
MAP is the commonly used abbreviation for the Market Access Program, a U.S. government initiative that helps promote the export of American agricultural products.
-
E.
MAP
MAP (Mobile Application Part) is a telecommunications protocol used in Signaling System No. 7 networks to support mobile services such as roaming, authentication, and SMS.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dcfc3430819095ee6fc0eb4c06a5 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c3d53e608190b8740c092b6e1523 |
completed | April 20, 2026, 6:12 a.m. |
Created at: April 10, 2026, 11:57 a.m.