Triple
T3580277
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary |
E75782
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Molly |
E254360
|
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: Molly | Statement: [Mary, hasVariant, Molly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Molly Context triple: [Mary, hasVariant, Molly]
-
A.
Molly
chosen
Molly is the central female protagonist in the 1926 silent film "Sparrows," portrayed by Mary Pickford.
-
B.
Maddy
Maddy is a common diminutive or nickname typically used for the given name Madison.
-
C.
Marylou
Marylou is a free-spirited, impulsive young woman who embodies the restless, hedonistic energy of the Beat Generation in Jack Kerouac’s novel "On the Road."
-
D.
Molly Ockett
Molly Ockett was a well-known Abenaki healer and folk figure from the 18th–19th century New England region, remembered for her medical skills, generosity, and close relationships with local settlers.
-
E.
Mollie Malloy
Mollie Malloy is a supporting character in the classic newsroom comedy "The Front Page," often portrayed as a vulnerable woman entangled in the central murder case and exploited by the press.
- 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_69ad85d5e3008190bdfe0bacdd1f5a1b |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc0ffecdc8190bf01c8ba90e3733e |
completed | March 8, 2026, 6:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b3bbc95fa881909846a6d53ba6a24e |
completed | March 13, 2026, 7:24 a.m. |
Created at: March 8, 2026, 3:21 p.m.