Triple
T12405578
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jacob Epstein |
E296375
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Jacob |
E283950
|
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: Jacob | Statement: [Jacob Epstein, givenName, Jacob]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jacob Context triple: [Jacob Epstein, givenName, Jacob]
-
A.
Jacob
Jacob is the full first name of Jack Lew, the American attorney and former U.S. Secretary of the Treasury.
-
B.
Jacob
chosen
Jacob is the birth name of legendary American comic book artist and writer Jack Kirby, a key creator of many iconic Marvel and DC superheroes.
-
C.
Jacob
Jacob is the first name of Jake Peavy, a former Major League Baseball pitcher and Cy Young Award winner.
-
D.
Jacob
Jacob is the family name of Piers Anthony, the prolific British-American fantasy and science fiction author best known for his long-running Xanth series.
-
E.
Jacob
Jacob is the middle name of Henry J. Friendly, a highly respected American federal appellate judge and legal scholar.
- 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_69d6ad9f464c81909db36d7e96e34b9e |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94d48f1908190918551c794f98fe3 |
completed | April 10, 2026, 7:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63efe60388190944fe3226be4cc7c |
completed | May 2, 2026, 6:14 p.m. |
Created at: April 8, 2026, 9:55 p.m.