Triple
T2657101
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mashdots |
E54638
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Grabar |
E229766
|
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: Grabar | Statement: [Mashdots, language, Grabar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Grabar Context triple: [Mashdots, language, Grabar]
-
A.
Grabar
chosen
Grabar is the classical form of the Armenian language used in literature, liturgy, and scholarship from antiquity through the Middle Ages.
-
B.
For the Record
"For the Record" is a song featured on the album E=MC² by Mariah Carey.
-
C.
Rockit
"Rockit" is a groundbreaking 1983 jazz-funk and electro track by Herbie Hancock, widely recognized for its innovative use of turntablism and music video that helped bring scratching into the mainstream.
-
D.
Eraser
Eraser is a 1996 action thriller film starring Arnold Schwarzenegger as a U.S. Marshal who protects a key witness while uncovering a high-tech weapons conspiracy.
-
E.
Grab
Grab is a Southeast Asian super-app company best known for its ride-hailing, food delivery, and digital payments services.
- 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_69ab49e028948190b97e01d73548b1d9 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd94c61a08190bdf5e1caeff3e788 |
completed | March 7, 2026, 7:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af98d535388190979a549dc2ce5f2f |
completed | March 10, 2026, 4:06 a.m. |
Created at: March 6, 2026, 9:53 p.m.