Triple
T1883588
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martínez |
E39908
|
entity |
| Predicate | relatedSurname |
P13741
|
FINISHED |
| Object | Martins |
E154782
|
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: Martins | Statement: [Martínez, relatedSurname, Martins]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Martins Context triple: [Martínez, relatedSurname, Martins]
-
A.
Martins
chosen
Martins is a common Portuguese and Spanish surname, often used as a patronymic meaning "son of Martin."
-
B.
Martz
Martz is a surname most notably associated with Mike Martz, an American football coach known for his innovative offensive strategies in the NFL.
-
C.
Fisher
Fisher is a common English surname borne by numerous notable individuals across fields such as economics, politics, entertainment, and sports.
-
D.
Mille
Mille is a French surname most notably borne by individuals such as Stéphane Mille.
-
E.
Fiske
Fiske is the middle name of Harlan F. Stone, who served as Chief Justice of the United States Supreme Court in the mid-20th century.
- 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_69a88633e4fc8190b7eb40463e048ec5 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb11d3cd48190bbd3ef2cf62e0dff |
completed | March 7, 2026, 5:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69addf5eabd8819089f267db92993033 |
completed | March 8, 2026, 8:43 p.m. |
Created at: March 4, 2026, 7:34 p.m.