Triple
T27112731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bell Temple of Tinsukia |
E686757
|
entity |
| Predicate | materialOffered |
P137026
|
FINISHED |
| Object | metal bells |
—
|
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: metal bells | Statement: [Bell Temple of Tinsukia, materialOffered, metal bells]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: materialOffered Context triple: [Bell Temple of Tinsukia, materialOffered, metal bells]
-
A.
offersMaterialIn
Indicates that an entity provides or makes available a particular material within a specified context, location, or medium.
-
B.
materialProvidedFor
Indicates that one entity supplies or makes available a material for use, processing, or incorporation by another entity or purpose.
-
C.
materialFound
Indicates that a particular material is present, discovered, or detected in association with a specified entity or location.
-
D.
materialUsed
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
E.
offeringMayInclude
chosen
Indicates that a particular offering can contain, comprise, or be associated with one or more specified components, items, or elements.
- 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_69ef148accd48190b6ed6e13a15f2a4f |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f65876c52c8190bc889c7a67bd07f3 |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 27, 2026, 8:54 a.m.