Triple
T2881395
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Jordan |
E59403
|
entity |
| Predicate | loveInterest |
P7325
|
FINISHED |
| Object | María |
E65513
|
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: María | Statement: [Robert Jordan, loveInterest, María]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: María Context triple: [Robert Jordan, loveInterest, María]
-
A.
María
chosen
María is a key character in Ernest Hemingway's novel "For Whom the Bell Tolls," known as a young Spanish woman and love interest of the protagonist amid the Spanish Civil War.
-
B.
María
"María" is a film featuring actress Taryn Power in a significant role.
-
C.
Luisa
Luisa is a feminine given name used in various languages, particularly Romance languages, as a form of the name Louise.
-
D.
Francisca
Francisca is a feminine given name, used in various European and Latin American cultures, that is cognate with the English name Frances.
-
E.
Amparo
Amparo is a municipality in the interior of Brazil known for its historical architecture and role in the coffee-producing region of the state of São Paulo.
- 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_69ab4ac739188190a112f42a5a69c951 |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abe02aa5948190a2e0bd9168232bd5 |
completed | March 7, 2026, 8:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b0864dc2fc8190bfc946ae454611c6 |
completed | March 10, 2026, 8:59 p.m. |
Created at: March 6, 2026, 10:03 p.m.