Triple
T10412591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hang Seng Index |
E245428
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object | HSI |
E325726
|
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: HSI | Statement: [Hang Seng Index, shortName, HSI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: HSI Context triple: [Hang Seng Index, shortName, HSI]
-
A.
HSI
chosen
HSI is the principal investigative arm of the U.S. Department of Homeland Security, responsible for enforcing federal laws related to border security, customs, immigration, and transnational crime.
-
B.
DSI
DSI is the Deutsches SOFIA Institut, a German research institute dedicated to supporting and conducting astronomical observations with the SOFIA airborne observatory.
-
C.
HWI
HWI is the National Rail station code for Horwich Parkway railway station in Greater Manchester, England.
-
D.
HWI
HWI is the vehicle registration code for the German town of Wismar in the state of Mecklenburg-Vorpommern.
-
E.
IHS
IHS is a U.S. federal agency within the Department of Health and Human Services that provides health services to American Indians and Alaska Natives.
- 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_69d381be340c8190b05998703d42d224 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4ea0e17f081908fb16425f65e5808 |
completed | April 7, 2026, 11:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d7fbfae96c8190ac496e9a1158afe4 |
completed | April 9, 2026, 7:20 p.m. |
Created at: April 6, 2026, 12:10 p.m.