Triple
T16256435
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ruth Shady |
E394640
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Ruth Shady |
E394641
|
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: Ruth Shady | Statement: [Ruth Shady, name, Ruth Shady]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ruth Shady Context triple: [Ruth Shady, name, Ruth Shady]
-
A.
Ruth Shady
chosen
Ruth Shady is a Peruvian archaeologist best known for uncovering and leading research on the ancient civilization at Caral, one of the oldest urban centers in the Americas.
-
B.
Ruth Rose
Ruth Rose was an American screenwriter best known for co-writing the classic 1933 monster film "King Kong."
-
C.
Ruth Josem
Ruth Josem is a private individual known primarily for being married to Jason Miller.
-
D.
Ruth Henshaw
Ruth Henshaw is a fictional character portrayed by American actress Frances Rafferty, likely in mid-20th-century film or television.
-
E.
Ruth Rumsey
Ruth Rumsey was the wife of William J. Donovan, the famed American soldier, lawyer, and head of the Office of Strategic Services during World War II.
- 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_69d87f2171208190951025e526947816 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2459a48f081909c76b38741b8f04e |
completed | April 17, 2026, 2:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0017b3b48c8190ad0043d730b1da35 |
completed | May 10, 2026, 5:29 a.m. |
Created at: April 10, 2026, 5:04 a.m.