Triple
T9452483
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Building 32, MIT |
E227926
|
entity |
| Predicate | houses |
P1643
|
FINISHED |
| Object | LIDS |
E228293
|
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: LIDS | Statement: [Building 32, MIT, houses, LIDS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LIDS Context triple: [Building 32, MIT, houses, LIDS]
-
A.
LIDS
chosen
LIDS is a research laboratory at MIT focused on advancing the theory and application of information and decision systems, including areas like control, communications, and machine learning.
-
B.
LYD
LYD is the ISO 4217 currency code for the Libyan dinar, the official currency of Libya.
-
C.
LYD
LYD is the station code for Lyon-Part-Dieu, a major high-speed rail hub and one of the main railway stations in Lyon, France.
-
D.
LIBID
LIBID is a globally unique identifier (GUID) used in Microsoft's Component Object Model to identify type libraries.
-
E.
IDIS
IDIS is a U.S. Department of Housing and Urban Development (HUD) information and financial management system used to plan, track, and report on the use of federal community development and housing funds.
- 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_69ca8439f8bc8190997f2ef40c9f0bc2 |
completed | March 30, 2026, 2:10 p.m. |
| NER | Named-entity recognition | batch_69cd7f68f9b081908bee041d4fc77e57 |
completed | April 1, 2026, 8:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d12272a2dc8190892a22db0799b6a4 |
completed | April 4, 2026, 2:38 p.m. |
Created at: March 30, 2026, 7:52 p.m.