Triple
T37550184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nandi |
E933570
|
entity |
| Predicate | oftenLocatedFacing |
P51444
|
FINISHED |
| Object | Shiva linga |
—
|
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: Shiva linga | Statement: [Nandi, oftenLocatedFacing, Shiva linga]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oftenLocatedFacing Context triple: [Nandi, oftenLocatedFacing, Shiva linga]
-
A.
oftenLocatedAs
Indicates that one entity is frequently found or situated in the same place as another entity.
-
B.
façadeOrientation
Indicates the directional orientation that a building’s façade faces relative to a reference (e.g., cardinal directions or a main street).
-
C.
oftenLocatedAt
Indicates that an entity is frequently or commonly found at, or associated with being in, a particular location.
-
D.
locationSide
chosen
Indicates that one entity is positioned on a particular side (e.g., left, right, front, back) relative to another entity or reference point.
-
E.
locatedAtCornerOf
Indicates that one entity is positioned at or forms the corner where two or more boundaries, edges, or intersecting paths meet.
- 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_69f76eca55bc8190acf25741793d5dac |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fe5d58c3e48190910aa3c23485e2c4 |
completed | May 8, 2026, 10:02 p.m. |
| PD | Predicate disambiguation | batch_69fe5c92090c8190bcfa412c0a3619df |
completed | May 8, 2026, 9:58 p.m. |
Created at: May 3, 2026, 4:17 p.m.