Triple
T7183630
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Béziers |
E167514
|
entity |
| Predicate | locatedOnRiver |
P165
|
FINISHED |
| Object | Orb |
E85347
|
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: Orb | Statement: [Béziers, locatedOnRiver, Orb]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Orb Context triple: [Béziers, locatedOnRiver, Orb]
-
A.
Orb
chosen
The Orb is a river in southern France that flows through the Occitanie region before emptying into the Mediterranean Sea.
-
B.
Orb
The Orb is a ceremonial piece of royal regalia symbolizing monarchical authority and Christian sovereignty, traditionally held by the monarch during British coronations.
-
C.
Orb
Orb is a biometric imaging device developed for the Worldcoin project that scans people’s irises to create unique digital identities.
-
D.
Orbe
The Orbe is a river in western Switzerland and eastern France that flows through the Jura region before joining the Aare river system.
-
E.
Orbiel
The Orbiel is a river in southern France that flows through the Aude department before joining the Aude River.
- 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_69c6888a7c548190a3d39b52a393080f |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e8de114c8190ad8fde0654526482 |
completed | March 27, 2026, 8:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7b94b058481909da9d5b21a5201de |
completed | March 28, 2026, 11:19 a.m. |
Created at: March 27, 2026, 2:49 p.m.