Triple
T17175471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David L. Parnas |
E416847
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Parnas |
E617242
|
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: Parnas | Statement: [David L. Parnas, familyName, Parnas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Parnas Context triple: [David L. Parnas, familyName, Parnas]
-
A.
Parnas
chosen
Parnas is a metro station in Saint Petersburg, Russia, serving as the northern terminus of one of the city’s subway lines.
-
B.
Yarshater
Yarshater is the surname of Ehsan Yarshater, a prominent Iranian historian and founding editor of the Encyclopaedia Iranica.
-
C.
Kalmus
Kalmus is a surname most notably associated with Herbert Kalmus, the co-founder of the pioneering color motion picture company Technicolor.
-
D.
Tatischeff
Tatischeff is the original family surname of French filmmaker and actor Jacques Tati, known for his influential comedic films and the character Monsieur Hulot.
-
E.
Prochiantz
Prochiantz is the surname of Alain Prochiantz, a prominent French neuroscientist known for his work on brain development and homeoprotein signaling.
- 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_69d886d5f34c8190b24564dfaa63f3fb |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3fc0cec448190b30466628a2ff23f |
completed | April 18, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0148435f6081909bfc6cc1ef59d971 |
completed | May 11, 2026, 3:08 a.m. |
Created at: April 10, 2026, 5:37 a.m.