Triple
T15015872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lockheed Martin Corporation |
E377957
|
entity |
| Predicate | hasStockTicker |
P1447
|
FINISHED |
| Object | LMT |
E77487
|
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: LMT | Statement: [Lockheed Martin Corporation, hasStockTicker, LMT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LMT Context triple: [Lockheed Martin Corporation, hasStockTicker, LMT]
-
A.
LMT
chosen
LMT is the stock ticker symbol for Lockheed Martin Corporation, a major American aerospace, defense, and security company.
-
B.
LKMT
LKMT is the ICAO airport code for Leoš Janáček Airport Ostrava, an international airport serving the Ostrava region in the Czech Republic.
-
C.
LTC
LTC is the commonly used abbreviation for the London Transit Commission, the public transportation agency serving the city of London, Ontario, Canada.
-
D.
Lm
Lm is the currency symbol that was used to denote the Maltese lira, Malta’s former national currency before adoption of the euro.
-
E.
MTM
MTM is the company responsible for operating Melbourne’s metropolitan passenger rail network in Victoria, Australia.
- 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_69d85cd3a3c881908c71fc424d459c17 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded7623c3c819092ca36b358b01842 |
completed | April 15, 2026, 12:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe9dd078e481908ec78db57541fc4c |
completed | May 9, 2026, 2:37 a.m. |
Created at: April 10, 2026, 2:55 a.m.