Triple
T18247118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jalsa Salana |
E436981
|
entity |
| Predicate | mediaCoverage |
P1782
|
FINISHED |
| Object | MTA International |
—
|
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: MTA International | Statement: [Jalsa Salana, mediaCoverage, MTA International]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MTA International Context triple: [Jalsa Salana, mediaCoverage, MTA International]
-
A.
MTA International
MTA International is a segment of the Italian stock exchange dedicated to the listing and trading of international companies’ shares.
-
B.
MTA International
chosen
MTA International is a global, multilingual satellite television network operated by the Ahmadiyya Muslim Community to broadcast religious, educational, and cultural programming worldwide.
-
C.
MTA
MTA is the commonly used abbreviation for the Maryland Transit Administration, the state agency that operates public transportation services in and around Baltimore, Maryland.
-
D.
MTA
MTA is the public transportation authority serving the New York City metropolitan area, operating subways, buses, and commuter rail systems.
-
E.
MTA
MTA is an abbreviation for the Project on Managing the Atom, a research initiative focused on nuclear policy, security, and governance.
- 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_69d8b91104e08190a8241f7d260a5162 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4f7e7d49c8190b227a13b63615754 |
completed | April 19, 2026, 3:42 p.m. |
Created at: April 10, 2026, 10:33 a.m.