Triple
T4627002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gare de Saint-Michel–Notre-Dame |
E101121
|
entity |
| Predicate | hasStationCode |
P1289
|
FINISHED |
| Object | SMND |
E335778
|
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: SMND | Statement: [Gare de Saint-Michel–Notre-Dame, hasStationCode, SMND]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SMND Context triple: [Gare de Saint-Michel–Notre-Dame, hasStationCode, SMND]
-
A.
SMND
chosen
SMND is the station code for the central Paris RER railway station Saint-Michel–Notre-Dame, a major hub near Notre-Dame Cathedral.
-
B.
SMA
SMA is the IATA airport code for the main airport serving Santa Maria Island in the Azores, Portugal.
-
C.
SMA
SMA is a radio interferometer observatory located on Maunakea in Hawaii that operates at submillimeter wavelengths to study astronomical objects such as star-forming regions, galaxies, and black holes.
-
D.
SMR
SMR is the three-letter ISO 3166-1 alpha-3 country code assigned to San Marino.
-
E.
SMN2
SMN2 is a human gene that produces a backup form of survival motor neuron protein and is a key therapeutic target in spinal muscular atrophy.
- 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_69bd43d0497c8190ac23c65c5804846a |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd5a0a7b588190bc6552ee5babb198 |
completed | March 20, 2026, 2:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bdfaafa6108190bad95e2a7e5a2ff8 |
completed | March 21, 2026, 1:55 a.m. |
Created at: March 20, 2026, 1:13 p.m.