Triple
T9270001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ETCS Level 2 |
E222799
|
entity |
| Predicate | developedBy |
P73
|
FINISHED |
| Object | UNISIG |
E788599
|
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: UNISIG | Statement: [ETCS Level 2, developedBy, UNISIG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: UNISIG Context triple: [ETCS Level 2, developedBy, UNISIG]
-
A.
UNISIG
chosen
UNISIG is an industrial consortium of railway suppliers that develops and maintains technical specifications and standards for the European Train Control System (ETCS).
-
B.
UNIS
UNIS is a Norwegian higher education and research institution located in Longyearbyen, Svalbard, specializing in Arctic studies and polar research.
-
C.
UNÎMES
UNÎMES is the acronym for the University of Nîmes, a French public higher education and research institution located in Nîmes, in the Occitanie region.
-
D.
Authenticum
Authenticum is a medieval Latin collection of the Novellae (new laws) of the Byzantine emperor Justinian I, widely used in Western European legal scholarship.
-
E.
SECG
SECG (Standards for Efficient Cryptography Group) is an industry consortium that develops and promotes standards for efficient public-key cryptography, particularly elliptic curve cryptography.
- 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_69ca841ffe208190aa7bcffbef2f8379 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd078525308190abfb883123742d3f |
completed | April 1, 2026, 11:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0b1ecfadc81909adf95fbbc77c389 |
completed | April 4, 2026, 6:38 a.m. |
Created at: March 30, 2026, 7:33 p.m.