Triple
T1391107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Jose Sharks |
E29959
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object |
SJS
SJS is the standard three-letter abbreviation for the San Jose Sharks, a professional ice hockey team in the National Hockey League.
|
E159971
|
NE FINISHED |
How this triple was built (4 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: SJS | Statement: [San Jose Sharks, abbreviation, SJS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SJS Context triple: [San Jose Sharks, abbreviation, SJS]
-
A.
S.J.
S.J. is the standard post-nominal abbreviation used to designate members of the Catholic religious order known as the Society of Jesus, or the Jesuits.
-
B.
TJSJ
TJSJ is the ICAO airport code for Luis Muñoz Marín International Airport, the main commercial airport serving San Juan, Puerto Rico.
-
C.
SJC
SJC is the abbreviation commonly used for the Massachusetts Supreme Judicial Court, the highest appellate court in the Commonwealth of Massachusetts.
-
D.
SJC
SJC is the three-letter FAA airport code for Norman Y. Mineta San Jose International Airport serving the San Jose, California area.
-
E.
SJR
SJR (SCImago Journal Rank) is a widely used bibliometric indicator that evaluates the scientific influence and prestige of academic journals by accounting for both the number and importance of citations they receive.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: SJS Triple: [San Jose Sharks, abbreviation, SJS]
Generated description
SJS is the standard three-letter abbreviation for the San Jose Sharks, a professional ice hockey team in the National Hockey League.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: SJS Target entity description: SJS is the standard three-letter abbreviation for the San Jose Sharks, a professional ice hockey team in the National Hockey League.
-
A.
S.J.
S.J. is the standard post-nominal abbreviation used to designate members of the Catholic religious order known as the Society of Jesus, or the Jesuits.
-
B.
TJSJ
TJSJ is the ICAO airport code for Luis Muñoz Marín International Airport, the main commercial airport serving San Juan, Puerto Rico.
-
C.
SJC
SJC is the abbreviation commonly used for the Massachusetts Supreme Judicial Court, the highest appellate court in the Commonwealth of Massachusetts.
-
D.
SJC
SJC is the three-letter FAA airport code for Norman Y. Mineta San Jose International Airport serving the San Jose, California area.
-
E.
SJR
SJR (SCImago Journal Rank) is a widely used bibliometric indicator that evaluates the scientific influence and prestige of academic journals by accounting for both the number and importance of citations they receive.
- F. None of above. chosen
Provenance (5 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_69a498dc92f8819094a1108f8ac90f43 |
completed | March 1, 2026, 7:51 p.m. |
| NER | Named-entity recognition | batch_69a4c35f7ab081909fe81dd475d6196f |
completed | March 1, 2026, 10:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acde24d1d88190bd6d602923270cd1 |
completed | March 8, 2026, 2:25 a.m. |
| NEDg | Description generation | batch_69acded052a88190945cf7a2af019c68 |
completed | March 8, 2026, 2:28 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69acdf41eb5c819088f2203f33995ccb |
completed | March 8, 2026, 2:30 a.m. |
Created at: March 1, 2026, 7:59 p.m.