Triple
T8979766
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liza Todd |
E214492
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Todd |
E105339
|
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: Todd | Statement: [Liza Todd, familyName, Todd]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Todd Context triple: [Liza Todd, familyName, Todd]
-
A.
Todd
chosen
Todd is the maiden surname of Mary Todd Lincoln, the First Lady of the United States during Abraham Lincoln’s presidency.
-
B.
Tim
Tim is the first name of American actor, writer, and director Tim Blake Nelson, known for his roles in films like "O Brother, Where Art Thou?" and "The Ballad of Buster Scruggs."
-
C.
Tim
Tim is the given name of Tim Wu, a prominent legal scholar and policy advocate known for coining the term "net neutrality."
-
D.
Tim
Tim is a fictional character from Robert Silverberg’s science fiction novel "The Book of Skulls," one of the four college students who seek an ancient order promising immortality at a terrible price.
-
E.
Tim
Tim is a fictional character portrayed by American actor Matt Bomer.
- 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_69ca839ea8b88190922c6a326ffcc0d3 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc67a615b081909b88e761be879802 |
completed | April 1, 2026, 12:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfc9719f5c8190bc22c3c7375b54f7 |
completed | April 3, 2026, 2:06 p.m. |
Created at: March 30, 2026, 7:03 p.m.