Triple
T21202279
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Punjabi Hindus |
E522485
|
entity |
| Predicate | majorityPresenceIn |
P84913
|
FINISHED |
| Object | Indian state of Punjab |
—
|
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: Indian state of Punjab | Statement: [Punjabi Hindus, majorityPresenceIn, Indian state of Punjab]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: majorityPresenceIn Context triple: [Punjabi Hindus, majorityPresenceIn, Indian state of Punjab]
-
A.
hasLargePresenceIn
Indicates that an entity maintains a significant or dominant level of activity, influence, or representation within a specified location, domain, or context.
-
B.
hasMajorityIn
Indicates that one entity holds more than half of the control, ownership, or representation within another entity or group.
-
C.
hasMajorityOf
Indicates that one entity possesses or controls more than half of the total quantity, members, or share of another entity.
-
D.
hostsMajorityOf
chosen
Indicates that one entity accommodates, contains, or supports more than half of the members or instances of another entity.
-
E.
hasMajority
Indicates that one entity holds more than half of the total share, control, or quantity in relation to another entity or set.
- 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_69e0b5112d8881909510b2dcdc93106d |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e73431973c81908c8682d7808a9d13 |
completed | April 21, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69e5f6094e3c81909ee9699e00d371f7 |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 3:19 p.m.