Triple
T18147613
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Jerome Newton |
E434427
|
entity |
| Predicate | formsRelationshipWith |
P61561
|
FINISHED |
| Object | Mary-Lou |
—
|
NE NERFINISHED |
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: Mary-Lou | Statement: [Thomas Jerome Newton, formsRelationshipWith, Mary-Lou]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary-Lou Context triple: [Thomas Jerome Newton, formsRelationshipWith, Mary-Lou]
-
A.
Mary-Lou
Mary-Lou is a timid, kind-hearted schoolgirl who appears as one of the students in Enid Blyton’s Malory Towers series.
-
B.
Mary-Louise
Mary-Louise is a feminine given name most notably associated with American actress Mary-Louise Parker.
-
C.
Mary Lou
Mary Lou is the first American woman gymnast to win the Olympic all-around gold medal, achieved at the 1984 Los Angeles Games.
-
D.
Mary Lou
Mary Lou is a feminine given name, typically a compound form of Mary and Lou, used in English-speaking countries.
-
E.
Mary Lou
Mary Lou is a technology innovator and entrepreneur best known for her pioneering work in display and imaging technologies, including co-founding One Laptop per Child and founding Openwater.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
Provenance (2 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_69d8b90aac308190801e2c57d8c5bfe5 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4de360ae88190abe1ed13243e9924 |
completed | April 19, 2026, 1:52 p.m. |
Created at: April 10, 2026, 10:29 a.m.