Triple
T23245893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Epigrams (Martial) |
E581581
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object | Martial |
—
|
NE NERFINISHED |
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: Martial | Statement: [Epigrams (Martial), author, Martial]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Martial Context triple: [Epigrams (Martial), author, Martial]
-
A.
Martial
chosen
Martial was a prominent Roman poet of the Silver Age renowned for his sharp, epigrammatic verses that satirized everyday life and society in ancient Rome.
-
B.
Marchal
Marchal is a fine-dining restaurant at Copenhagen’s historic Hôtel d’Angleterre, known for its elegant Nordic-French cuisine and refined atmosphere.
-
C.
Barrière du Combat
Barrière du Combat was a former toll gate of the Wall of the Farmers-General in Paris, historically marking an entrance to the city and associated with the nearby Place du Combat (now Place du Colonel Fabien).
-
D.
Guerrière
Guerrière was a French warship that took part in the decisive 1827 naval Battle of Navarino during the Greek War of Independence.
-
E.
De Lutte
De Lutte is a village in the municipality of Losser in the Dutch province of Overijssel, known for its scenic countryside and proximity to the German border.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e24606b17c81908aba1a4911c8a8ba |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f193f0f5d88190a497f14601f9bf29 |
completed | April 29, 2026, 5:15 a.m. |
Created at: April 17, 2026, 4:10 p.m.