Triple
T4936508
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Varaha |
E110823
|
entity |
| Predicate | mount |
P18930
|
FINISHED |
| Object | Garuda |
E108946
|
NE 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: Garuda | Statement: [Varaha, mount, Garuda]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Garuda Context triple: [Varaha, mount, Garuda]
-
A.
Garuda
chosen
Garuda is a legendary bird-like divine being in Hindu mythology, revered as the king of birds and the powerful vehicle of the god Vishnu.
-
B.
GARUDA
GARUDA is the radio callsign used by Garuda Indonesia, the national flag carrier airline of Indonesia.
-
C.
Falkor
Falkor is the luckdragon from Michael Ende’s fantasy novel "The Neverending Story," known for his benevolent nature, flying abilities, and role as the protagonist’s loyal companion.
-
D.
Palas
Palas is a remote valley and settlement in Pakistan’s Kohistan region, known for its rugged terrain, rich biodiversity, and traditional mountain communities.
-
E.
Palas
Palas is the main residential and ceremonial building within Nuremberg Castle, historically used as the living quarters and audience hall of the ruling nobility.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd4415eee08190bdce70276e56a5b4 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd7085b1dc819099408f6503f0210f |
completed | March 20, 2026, 4:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be77ba40f881908452455ad55221e5 |
completed | March 21, 2026, 10:49 a.m. |
Created at: March 20, 2026, 1:30 p.m.