Triple
T16274172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hugh d'Avranches |
E395080
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object | Lupus |
E472717
|
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: Lupus | Statement: [Hugh d'Avranches, nickname, Lupus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lupus Context triple: [Hugh d'Avranches, nickname, Lupus]
-
A.
Lupus
chosen
Lupus is a small, faint constellation in the southern sky, traditionally depicted as a wolf or wild animal.
-
B.
SLE
SLE is a mid-level trim package for GMC vehicles that typically adds upgraded comfort, convenience, and appearance features over the base model.
-
C.
SLE
SLE is a commuter rail service operating along the Connecticut shoreline, connecting towns between New London and New Haven.
-
D.
SLE
SLE is the IATA airport code for Salem Municipal Airport, a public airport serving Salem, Oregon, in the United States.
-
E.
SLE
SLE (Software Language Engineering) is a conference focused on the theory, design, implementation, and application of software languages and language-based tools.
- 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_69d87f221d8081909b0b2063e7528ba2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2460c2d948190813b66e539a64a70 |
completed | April 17, 2026, 2:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0017c0ef4c8190b44ac84f71b2ed41 |
completed | May 10, 2026, 5:29 a.m. |
Created at: April 10, 2026, 5:05 a.m.