Triple
T16697436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IN-HR |
E405750
|
entity |
| Predicate | codeSet |
P14765
|
FINISHED |
| Object | ISO 3166-2:IN |
E100868
|
NE 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: ISO 3166-2:IN | Statement: [IN-HR, codeSet, ISO 3166-2:IN]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ISO 3166-2:IN Context triple: [IN-HR, codeSet, ISO 3166-2:IN]
-
A.
ISO 3166-2:IN
chosen
ISO 3166-2:IN is the section of the ISO 3166 standard that defines internationally recognized subdivision codes for the states and union territories of India.
-
B.
ISO 3166-2:CR
ISO 3166-2:CR is the ISO 3166-2 entry that defines the official subdivision codes for the provinces of Costa Rica.
-
C.
ISO 3166-2:ST
ISO 3166-2:ST is the ISO 3166-2 entry that defines the principal subdivision codes for São Tomé and Príncipe.
-
D.
ISO 3166-2:SM
ISO 3166-2:SM is the subdivision code set within the ISO 3166-2 standard that defines codes for the principal subdivisions of San Marino.
-
E.
ISO 3166-2:PK
ISO 3166-2:PK is the section of the ISO 3166-2 standard that defines the official subdivision codes for the provinces and territories of Pakistan.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d8838db21081909589220fd71440a4 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3832e93c48190a594c498e9cc901a |
completed | April 18, 2026, 1:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00919d02088190acecb1a62a100255 |
completed | May 10, 2026, 2:09 p.m. |
Created at: April 10, 2026, 5:19 a.m.