Triple
T9746450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marc Connelly |
E236321
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Marc |
E48930
|
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: Marc | Statement: [Marc Connelly, givenName, Marc]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marc Context triple: [Marc Connelly, givenName, Marc]
-
A.
Marc
chosen
Marc is the given name of Marc Andreessen, the influential American entrepreneur, software engineer, and venture capitalist known for co-creating the Mosaic web browser and co-founding Netscape and Andreessen Horowitz.
-
B.
Marcus
Marcus is a masculine given name of ancient Roman origin that has been widely used across many cultures and historical periods.
-
C.
Markus
Markus is the given first name of the renowned abstract expressionist painter Mark Rothko.
-
D.
Markus
Markus is the first name of American professional baseball star Mookie Betts.
-
E.
Andre
Andre is the given name of Andre Reed, a former American football wide receiver best known for his long career with the Buffalo Bills in the NFL.
- 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_69ca84d3e24481908a476e2231123cf9 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9f65ad788190b68d731b6f516d93 |
completed | April 1, 2026, 10:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1b004a6e88190a974f4a8973f91ef |
completed | April 5, 2026, 12:42 a.m. |
Created at: March 30, 2026, 8:23 p.m.