Triple
T14807007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wanda De Jesus |
E348063
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | De Jesus |
E815552
|
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: De Jesus | Statement: [Wanda De Jesus, familyName, De Jesus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: De Jesus Context triple: [Wanda De Jesus, familyName, De Jesus]
-
A.
Jesús María
Jesús María is a municipality in the Mexican state of Aguascalientes, known for its growing urban area and integration into the metropolitan region of the state capital.
-
B.
Jesús María
Jesús María is a small city in the Los Altos region of Jalisco, Mexico, known for its traditional Mexican culture and agricultural surroundings.
-
C.
Jesús María
Jesús María is a small city in central Argentina known for its traditional folklore and horse-taming festival.
-
D.
De Jesús
chosen
De Jesús is the family name of Puerto Rican singer-songwriter Kany García, reflecting her full birth name Encarnita García De Jesús.
-
E.
Santi
Santi is the ghost of a murdered boy who haunts a remote orphanage in Guillermo del Toro’s gothic horror film "The Devil’s Backbone."
- 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_69d822ea8b7c819097dfadf3d45545e6 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69decf33b6a08190ab6a4cfeda2cc09c |
completed | April 14, 2026, 11:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe24c8bc6881908736c029943997ae |
completed | May 8, 2026, 6 p.m. |
Created at: April 10, 2026, 1:41 a.m.