Triple
T29395077
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vandiyur Mariamman Temple |
E745471
|
entity |
| Predicate | nearbyCityLandmark |
P61270
|
FINISHED |
| Object | Madurai Meenakshi Amman Temple (same city) |
—
|
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: Madurai Meenakshi Amman Temple (same city) | Statement: [Vandiyur Mariamman Temple, nearbyCityLandmark, Madurai Meenakshi Amman Temple (same city)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nearbyCityLandmark Context triple: [Vandiyur Mariamman Temple, nearbyCityLandmark, Madurai Meenakshi Amman Temple (same city)]
-
A.
typicalNearbyLandmarks
Indicates that certain landmarks are commonly found in the vicinity of a given place or location.
-
B.
nearbyUrbanCenter
Indicates that one location is geographically close to an urban center, such as a city or large town.
-
C.
nearbyLocation
chosen
Indicates that one location is situated close to another location in physical space.
-
D.
nearbyHeritageDestinations
Indicates that one or more heritage destinations are located close to a given reference point or entity in geographic space.
-
E.
nearestCityTo
Indicates that one city is the closest in distance to a given location or entity compared to all other cities.
- 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_69f0a79dfabc81908755382ee47791e2 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69fcec5f8b448190b48330a19b462d24 |
completed | May 7, 2026, 7:47 p.m. |
| PD | Predicate disambiguation | batch_69fceaf1e23881908ca24160a638e329 |
completed | May 7, 2026, 7:41 p.m. |
Created at: April 28, 2026, 2:45 p.m.