Triple
T3252555
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geʽez |
E68214
|
entity |
| Predicate | influenced |
P9
|
FINISHED |
| Object | Tigre |
E87133
|
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: Tigre | Statement: [Geʽez, influenced, Tigre]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tigre Context triple: [Geʽez, influenced, Tigre]
-
A.
Tigre
chosen
Tigre is a Semitic Afroasiatic language spoken primarily by the Tigre people in Eritrea and parts of Sudan.
-
B.
Leone
Leone is a village on the island of Tutuila in American Samoa, known for its coastal setting and traditional Samoan culture.
-
C.
Tapirira
Tapirira is a genus of tropical trees in the cashew and sumac family, known for species that often dominate lowland Neotropical forests.
-
D.
Pumas
The Pumas are Argentina's national rugby union team, known for competing at the highest international level, including in major tournaments like The Rugby Championship and the Rugby World Cup.
-
E.
Pumas
Pumas is a popular Mexican professional football club based in Mexico City, officially known as Club Universidad Nacional.
- 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_69ad858f74408190bcbd07f967cd7bd0 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaf440bb88190a2450405afae7f1f |
completed | March 8, 2026, 5:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2776e9ad88190a59edf4735703e8d |
completed | March 12, 2026, 8:21 a.m. |
Created at: March 8, 2026, 3:09 p.m.