Triple
T37114452
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mhasla |
E919079
|
entity |
| Predicate | servesAsMarketTownFor |
P61448
|
FINISHED |
| Object | surrounding villages |
—
|
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: surrounding villages | Statement: [Mhasla, servesAsMarketTownFor, surrounding villages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesAsMarketTownFor Context triple: [Mhasla, servesAsMarketTownFor, surrounding villages]
-
A.
marketTown
chosen
Indicates that a town functions as a local commercial center where markets are regularly held for trade and exchange.
-
B.
containsMarketTown
Indicates that one region or area includes within its boundaries a town that functions as a market center.
-
C.
isInMarketTown
Indicates that an entity is located within or belongs to a town that functions as a local commercial or trading center.
-
D.
hasMarketTownStatus
Indicates that a settlement holds the official legal or historical status of being recognized as a market town.
-
E.
isParishSeatOf
Indicates that a location serves as the administrative center or main seat of government for a particular parish.
- 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_69f76e9c57148190ba789dd059645bb9 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a005e8a2f7c819085bfc6f04b866d87 |
completed | May 10, 2026, 10:31 a.m. |
| PD | Predicate disambiguation | batch_6a005de82ef08190a015b385d1d3443c |
completed | May 10, 2026, 10:28 a.m. |
Created at: May 3, 2026, 4:15 p.m.